---
title: "Personality Alignment of Large Language Models — Zhu 2024"
description: "Instead they propose PAS (Personality Activation Search). 114 references, cited by 20 papers here."
authors: ["Minjun Zhu", "Yixuan Weng", "Linyi Yang", "Yue Zhang"]
year: 2024
venue: "arXiv:2408.11779"
source: "https://arxiv.org/abs/2408.11779"
doi: "10.48550/arxiv.2408.11779"
arxiv: "2408.11779"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhu-2024-personality-alignment-large-language-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhu-2024-personality-alignment-large-language-models/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/8/) / Personality Alignment of Large Language Models

# Personality Alignment of Large Language Models

**Authors:** [Minjun Zhu](https://md.research.elamur.ai/free/en/authors/minjun-zhu/), [Yixuan Weng](https://md.research.elamur.ai/free/en/authors/yixuan-weng/), [Linyi Yang](https://md.research.elamur.ai/free/en/authors/linyi-yang/) and [Yue Zhang](https://md.research.elamur.ai/free/en/authors/yue-zhang/) · **Year:** 2024 · **Venue:** arXiv:2408.11779 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2408.11779) · [PDF](https://arxiv.org/pdf/2408.11779) · [DOI 10.48550/arxiv.2408.11779](https://doi.org/10.48550/arxiv.2408.11779) · [arXiv 2408.11779](https://arxiv.org/abs/2408.11779) · [OpenAlex](https://openalex.org/W4405418952)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [20](https://md.research.elamur.ai/free/en/papers/zhu-2024-personality-alignment-large-language-models/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Standard LLM alignment targets broad, shared human values and ignores how individual users differ. The authors call this gap "Personality Alignment": adapting a model's answers and choices to one person or a small, closely related group. To make the task measurable, they build PAPI, a psychometrics-based dataset that combines Big Five inventories with the Dark Triad. This lets alignment be checked on both benign and potentially harmful traits. Per-user data is scarce, and the approach must scale to many users, so the authors avoid RLHF-style fine-tuning. Instead they propose PAS (Personality Activation Search). PAS finds attention heads whose activations track personality traits, shifts activations along those directions and searches for the best shift size, all without backpropagation. The paper reports that PAS beats DPO with a fraction of its optimization time. It also reports that Llama-3-8B with PAS outperforms GPT-4o. The work points toward cheap, user-centred assistants, and the dataset and code are public (github.com/zhu-minjun/PAlign).

## Key points
- **PAPI dataset:** It covers more than 320,000 real subjects. Over 300,000 of them completed the IPIP-NEO-120 and IPIP-NEO-300 questionnaires through the IPIP website, and the responses were anonymized.
- **Dark Triad component:** 18,192 separate samples come from the 27-item Short Dark Triad, which measures Machiavellianism, Narcissism and Psychopathy.
- **Test sets:** 300 representative subjects were held out from each assessment. The Big Five test set has a mean score of 3.11, which the authors use as evidence that it is representative.
- **PAS method:** PAS works by activation steering. It optimizes both the direction and the magnitude of shifts across several personality dimensions at once. Earlier activation steering work optimized a single goal such as safety or truthfulness.
- **Efficiency:** The abstract says PAS needs about 1/5 of DPO's optimization time. The introduction gives about 1/6 relative to DPO and PPO. In both cases PAS is reported to align better than these baselines.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University College London](https://md.research.elamur.ai/free/en/universities/university-college-london/) — University, London, United Kingdom · 88 works · 19,432 citations
- [Huawei Technologies](https://md.research.elamur.ai/free/en/companies/huawei-technologies/) — Company, Shenzhen, China · 75 works · 12,975 citations
- [Westlake University](https://md.research.elamur.ai/free/en/universities/westlake-university/) — University, Hangzhou, China · 45 works · 8,028 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Safety Research](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · 543 works

🧭 Topics (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works

## Cite

Cite as: Minjun Zhu, Yixuan Weng, Linyi Yang and Yue Zhang. 2024. Personality Alignment of Large Language Models. arXiv:2408.11779.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{zhu2024personality,
  title = {{Personality Alignment of Large Language Models}},
  author = {Minjun Zhu, Yixuan Weng, Linyi Yang and Yue Zhang},
  year = {2024},
  doi = {10.48550/arxiv.2408.11779},
  eprint = {2408.11779},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2408.11779}
}
```

- [← previous MoRAL: MoE Augmented LoRA for LLMs' Lifelong Learning](https://md.research.elamur.ai/free/en/papers/yang-2024-moral-moe-augmented-lora-llms/)
- [next → Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models](https://md.research.elamur.ai/free/en/papers/wei-2024-skywork-moe-deep-dive/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/8/)

## References

114 references, 44 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Gati V Aher, Rosa I Arriaga, and Adam Tauman Kalai. Using large language models to simulate multiple humans and replicate human subject studies. In International Conference on Machine Learning, pp. 337–371. PMLR, 2023. [find](https://scholar.google.com/scholar?q=Gati+V+Aher%2C+Rosa+I+Arriaga%2C+and+Adam+Tauman+Kalai%2E+Using+large+language+models+to+simulate+multiple+humans+and+replicate+human+subject+studies%2E+In+International+Conference+on+Machine+Learning%2C+pp%2E+33)
2. Meta AI. Introducing meta llama 3: The most capable openly available llm to date. [https://ai.meta.com/blog/meta-llama-3/](https://ai.meta.com/blog/meta-llama-3/), 2024. Accessed: 2024-05-21. [↗](https://ai.meta.com/blog/meta-llama-3/)
3. Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, Alessandro Cappelli, Ruxandra Cojocaru, Mérouane Debbah, Étienne Goffinet, Daniel Hesslow, Julien Launay, Quentin Malartic, et al. [The falcon series of open language models](https://md.research.elamur.ai/free/en/papers/almazrouei-2023-falcon-series-open-language-models/). arXiv preprint arXiv:2311.16867, 2023.
4. Anton Aluja and Luis F Garcia. Relationships between big five personality factors and values. Social Behavior and Personality: an international journal, 32(7):619–625, 2004. [find](https://scholar.google.com/scholar?q=Anton+Aluja+and+Luis+F+Garcia%2E+Relationships+between+big+five+personality+factors+and+values%2E+Social+Behavior+and+Personality%3A+an+international+journal%2C+32%287%29%3A619%E2%80%93625%2C+2004%2E)
5. Patel Arkil, Bhattamishra Satwik, and Goyal Navin. [Are nlp models really able to solve simple math word problems?](https://md.research.elamur.ai/free/en/papers/patel-2021-are-nlp-models-really-able/) 2021.
6. Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, Daniel Guo, Daniele Calandriello, Michal Valko, and Rémi Munos. [A general theoretical paradigm to understand learning from human preferences](https://md.research.elamur.ai/free/en/papers/azar-2023-general-theoretical-paradigm-understand-learning/), 2023.
7. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. [Qwen technical report](https://md.research.elamur.ai/free/en/papers/bai-2023-qwen-technical-report/). arXiv preprint arXiv:2309.16609, 2023.
8. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862, 2022a. [find](https://scholar.google.com/scholar?q=Yuntao+Bai%2C+Andy+Jones%2C+Kamal+Ndousse%2C+Amanda+Askell%2C+Anna+Chen%2C+Nova+DasSarma%2C+Dawn+Drain%2C+Stanislav+Fort%2C+Deep+Ganguli%2C+Tom+Henighan%2C+et+al%2E+Training+a+helpful+and+harmless+assistant+with+reinforcem)
9. Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, et al. [Constitutional ai: Harmlessness from ai feedback](https://md.research.elamur.ai/free/en/papers/bai-2022-constitutional-ai-harmlessness-ai-feedback/). arXiv preprint arXiv:2212.08073, 2022b.
10. Tom L Beauchamp et al. The belmont report. The Oxford textbook of clinical research ethics, pp. 149–155, 2008. [find](https://scholar.google.com/scholar?q=Tom+L+Beauchamp+et+al%2E+The+belmont+report%2E+The+Oxford+textbook+of+clinical+research+ethics%2C+pp%2E+149%E2%80%93155%2C+2008%2E)
11. Collin Burns, Haotian Ye, Dan Klein, and Jacob Steinhardt. Discovering latent knowledge in language models without supervision. In The Eleventh International Conference on Learning Representations, 2023a. URL [https://openreview.net/forum?id=ETKGuby0hcs](https://openreview.net/forum?id=ETKGuby0hcs). [↗](https://openreview.net/forum?id=ETKGuby0hcs)
12. Collin Burns, Haotian Ye, Dan Klein, and Jacob Steinhardt. Discovering latent knowledge in language models without supervision. In The Eleventh International Conference on Learning Representations, 2023b. URL [https://openreview.net/forum?id=ETKGuby0hcs](https://openreview.net/forum?id=ETKGuby0hcs). [↗](https://openreview.net/forum?id=ETKGuby0hcs)
13. Andres Carranza, Dhruv Bhandarkar Pai, Rylan Schaeffer, Arnuv Tandon, and Sanmi Koyejo. Deceptive alignment monitoring. In The Second Workshop on New Frontiers in Adversarial Machine Learning, 2023. URL [https://openreview.net/forum?id=obsO44GFhh](https://openreview.net/forum?id=obsO44GFhh). [↗](https://openreview.net/forum?id=obsO44GFhh)
14. Heather EP Cattell and Alan D Mead. The sixteen personality factor questionnaire (16pf). The SAGE handbook of personality theory and assessment, 2:135–159, 2008. [find](https://scholar.google.com/scholar?q=Heather+EP+Cattell+and+Alan+D+Mead%2E+The+sixteen+personality+factor+questionnaire+%2816pf%29%2E+The+SAGE+handbook+of+personality+theory+and+assessment%2C+2%3A135%E2%80%93159%2C+2008%2E)
15. Jiangjie Chen, Xintao Wang, Rui Xu, Siyu Yuan, Yikai Zhang, Wei Shi, Jian Xie, Shuang Li, Ruihan Yang, Tinghui Zhu, Aili Chen, Nianqi Li, Lida Chen, Caiyu Hu, Siye Wu, Scott Ren, Ziquan Fu, and Yanghua Xiao. [From persona to personalization: A survey on role-playing language agents](https://md.research.elamur.ai/free/en/papers/chen-2024-persona-personalization-survey-role-playing/), 2024.
16. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168, 2021.
17. Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, and Yaodong Yang. [Safe RLHF: Safe reinforcement learning from human feedback](https://md.research.elamur.ai/free/en/papers/dai-2023-safe-rlhf-safe-reinforcement-learning/). In The Twelfth International Conference on Learning Representations, 2024. URL [https://openreview.net/forum?](https://openreview.net/forum?) id=TyFrPOKYXw. [↗](https://openreview.net/forum?)
18. Boele De Raad. The big five personality factors: the psycholexical approach to personality. Hogrefe & Huber Publishers, 2000. [find](https://scholar.google.com/scholar?q=Boele+De+Raad%2E+The+big+five+personality+factors%3A+the+psycholexical+approach+to+personality%2E+Hogrefe+%26+Huber+Publishers%2C+2000%2E)
19. Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale. Advances in Neural Information Processing Systems, 35: 30318–30332, 2022. [find](https://scholar.google.com/scholar?q=Tim+Dettmers%2C+Mike+Lewis%2C+Younes+Belkada%2C+and+Luke+Zettlemoyer%2E+Gpt3%2E+int8+%28%29%3A+8%2Dbit+matrix+multiplication+for+transformers+at+scale%2E+Advances+in+Neural+Information+Processing+Systems%2C+35%3A+30318%E2%80%9330332)
20. Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. [Qlora: Efficient finetuning of quantized llms](https://md.research.elamur.ai/free/en/papers/dettmers-2023-qlora-efficient-finetuning-quantized-llms/). ArXiv, abs/2305.14314, 2023. URL [https://api.semanticscholar.org/CorpusID:258841328](https://api.semanticscholar.org/CorpusID:258841328). [↗](https://api.semanticscholar.org/CorpusID:258841328)
21. Daniel Dewey. Learning what to value. In International conference on artificial general intelligence, pp. 309–314. Springer, 2011. [find](https://scholar.google.com/scholar?q=Daniel+Dewey%2E+Learning+what+to+value%2E+In+International+conference+on+artificial+general+intelligence%2C+pp%2E+309%E2%80%93314%2E+Springer%2C+2011%2E)
22. Hanze Dong, Wei Xiong, Deepanshu Goyal, Yihan Zhang, Winnie Chow, Rui Pan, Shizhe Diao, Jipeng Zhang, KaShun SHUM, and Tong Zhang. [RAFT: Reward ranked finetuning for generative foundation model alignment](https://md.research.elamur.ai/free/en/papers/dong-2023-raft-reward-ranked-finetuning-generative/). Transactions on Machine Learning Research, 2023. ISSN 2835-8856. URL [https://openreview.net/for…](https://openreview.net/for…) [↗](https://openreview.net/for…)
23. Esin Durmus, Karina Nyugen, Thomas I Liao, Nicholas Schiefer, Amanda Askell, Anton Bakhtin, Carol Chen, Zac Hatfield-Dodds, Danny Hernandez, Nicholas Joseph, et al. [Towards measuring the representation of subjective global opinions in language models](https://md.research.elamur.ai/free/en/papers/durmus-2023-towards-measuring-representation-subjective-global/). arXiv preprint arXiv:2306.16388, 2023.
24. Lilian Edwards. The eu ai act: a summary of its significance and scope. Artificial Intelligence (the EU AI Act), 1, 2021. [find](https://scholar.google.com/scholar?q=Lilian+Edwards%2E+The+eu+ai+act%3A+a+summary+of+its+significance+and+scope%2E+Artificial+Intelligence+%28the+EU+AI+Act%29%2C+1%2C+2021%2E)
25. Mirko Farina and Andrea Lavazza. Chatgpt in society: emerging issues. Frontiers in Artificial Intelligence, 6:1130913, 2023. [find](https://scholar.google.com/scholar?q=Mirko+Farina+and+Andrea+Lavazza%2E+Chatgpt+in+society%3A+emerging+issues%2E+Frontiers+in+Artificial+Intelligence%2C+6%3A1130913%2C+2023%2E)
26. Patrick Fernandes, Aman Madaan, Emmy Liu, António Farinhas, Pedro Henrique Martins, Amanda Bertsch, José G. C. de Souza, Shuyan Zhou, Tongshuang Wu, Graham Neubig, and André F. T. Martins. [Bridging the gap: A survey on integrating (human) feedback for natural language generation](https://md.research.elamur.ai/free/en/papers/fernandes-2023-bridging-gap-survey-integrating-human/), 2023.
27. Phoebe Friesen, Lisa Kearns, Barbara Redman, and Arthur L Caplan. Rethinking the belmont report? The American Journal of Bioethics, 17(7):15–21, 2017. [find](https://scholar.google.com/scholar?q=Phoebe+Friesen%2C+Lisa+Kearns%2C+Barbara+Redman%2C+and+Arthur+L+Caplan%2E+Rethinking+the+belmont+report%3F+The+American+Journal+of+Bioethics%2C+17%287%29%3A15%E2%80%9321%2C+2017%2E)
28. Mor Geva, Jasmijn Bastings, Katja Filippova, and Amir Globerson. Dissecting recall of factual associations in auto-regressive language models. In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 12216–12235,… [find](https://scholar.google.com/scholar?q=Mor+Geva%2C+Jasmijn+Bastings%2C+Katja+Filippova%2C+and+Amir+Globerson%2E+Dissecting+recall+of+factual+associations+in+auto%2Dregressive+language+models%2E+In+Houda+Bouamor%2C+Juan+Pino%2C+and+Kalika+Bali+%28eds%2E%29%2C+Proc)
29. Dongyoung Go, Tomasz Korbak, Germán Kruszewski, Jos Rozen, and Marc Dymetman. Compositional preference models for aligning lms. arXiv preprint arXiv:2310.13011, 2023. — [arXiv:2310.13011](https://arxiv.org/abs/2310.13011) [find](https://scholar.google.com/scholar?q=Dongyoung+Go%2C+Tomasz+Korbak%2C+Germ%C3%A1n+Kruszewski%2C+Jos+Rozen%2C+and+Marc+Dymetman%2E+Compositional+preference+models+for+aligning+lms%2E+arXiv+preprint+arXiv%3A2310%2E13011%2C+2023%2E+%E2%80%94+%5BarXiv%3A2310%2E13011%5D%28https%3A%2F%2Farxi)
30. Lewis R Goldberg et al. A broad-bandwidth, public domain, personality inventory measuring the lower-level facets of several five-factor models. Personality psychology in Europe, 7(1):7–28, 1999. [find](https://scholar.google.com/scholar?q=Lewis+R+Goldberg+et+al%2E+A+broad%2Dbandwidth%2C+public+domain%2C+personality+inventory+measuring+the+lower%2Dlevel+facets+of+several+five%2Dfactor+models%2E+Personality+psychology+in+Europe%2C+7%281%29%3A7%E2%80%9328%2C+1999%2E)
31. Nicholas Goldowsky-Dill, Chris MacLeod, Lucas Sato, and Aryaman Arora. Localizing model behavior with path patching. arXiv preprint arXiv:2304.05969, 2023. [find](https://scholar.google.com/scholar?q=Nicholas+Goldowsky%2DDill%2C+Chris+MacLeod%2C+Lucas+Sato%2C+and+Aryaman+Arora%2E+Localizing+model+behavior+with+path+patching%2E+arXiv+preprint+arXiv%3A2304%2E05969%2C+2023%2E)
32. Akshat Gupta, Xiaoyang Song, and Gopala Anumanchipalli. Self-assessment tests are unreliable measures of LLM personality. In Yonatan Belinkov, Najoung Kim, Jaap Jumelet, Hosein Mohebbi, Aaron Mueller, and Hanjie Chen (eds.), Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neu… [find](https://scholar.google.com/scholar?q=Akshat+Gupta%2C+Xiaoyang+Song%2C+and+Gopala+Anumanchipalli%2E+Self%2Dassessment+tests+are+unreliable+measures+of+LLM+personality%2E+In+Yonatan+Belinkov%2C+Najoung+Kim%2C+Jaap+Jumelet%2C+Hosein+Mohebbi%2C+Aaron+Mueller%2C)
33. Shashank Gupta, Vaishnavi Shrivastava, Ameet Deshpande, Ashwin Kalyan, Peter Clark, Ashish Sabharwal, and Tushar Khot. Bias runs deep: Implicit reasoning biases in persona-assigned LLMs. In The Twelfth International Conference on Learning Representations, 2024b. URL [https://openreview.net/forum?id=k…](https://openreview.net/forum?id=k…) [↗](https://openreview.net/forum?id=k…)
34. Dorit Hadar-Shoval, Kfir Asraf, Yonathan Mizrachi, Yuval Haber, and Zohar Elyoseph. Assessing the alignment of large language models with human values for mental health integration: Cross-sectional study using schwartz’s theory of basic values. JMIR Mental Health, 11:e55988, 2024. [find](https://scholar.google.com/scholar?q=Dorit+Hadar%2DShoval%2C+Kfir+Asraf%2C+Yonathan+Mizrachi%2C+Yuval+Haber%2C+and+Zohar+Elyoseph%2E+Assessing+the+alignment+of+large+language+models+with+human+values+for+mental+health+integration%3A+Cross%2Dsectional+st)
35. Zhezhi He, Adnan Siraj Rakin, and Deliang Fan. Parametric noise injection: Trainable randomness to improve deep neural network robustness against adversarial attack. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 588–597, 2019. [find](https://scholar.google.com/scholar?q=Zhezhi+He%2C+Adnan+Siraj+Rakin%2C+and+Deliang+Fan%2E+Parametric+noise+injection%3A+Trainable+randomness+to+improve+deep+neural+network+robustness+against+adversarial+attack%2E+In+Proceedings+of+the+IEEE%2FCVF+Con)
36. Dan Hendrycks, Mantas Mazeika, and Thomas Woodside. An overview of catastrophic ai risks, 2023. [find](https://scholar.google.com/scholar?q=Dan+Hendrycks%2C+Mantas+Mazeika%2C+and+Thomas+Woodside%2E+An+overview+of+catastrophic+ai+risks%2C+2023%2E)
37. Joe Hoover, Gwenyth Portillo-Wightman, Leigh Yeh, Shreya Havaldar, Aida Mostafazadeh Davani, Ying Lin, Brendan Kennedy, Mohammad Atari, Zahra Kamel, Madelyn Mendlen, Gabriela Moreno, Christina Park, Tingyee E. Chang, Jenna Chin, Christian Leong, Jun Yen Leung, Arineh Mirinjian, and Morteza Dehghani.… [find](https://scholar.google.com/scholar?q=Joe+Hoover%2C+Gwenyth+Portillo%2DWightman%2C+Leigh+Yeh%2C+Shreya+Havaldar%2C+Aida+Mostafazadeh+Davani%2C+Ying+Lin%2C+Brendan+Kennedy%2C+Mohammad+Atari%2C+Zahra+Kamel%2C+Madelyn+Mendlen%2C+Gabriela+Moreno%2C+Christina+Park%2C+T)
38. Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. [Learning to solve arithmetic word problems with verb categorization](https://md.research.elamur.ai/free/en/papers/hosseini-2014-learning-solve-arithmetic-word-problems/). empirical methods in natural language processing, 2014.
39. J. Edward Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ArXiv, abs/2106.09685, 2021. URL [https://api.semanticscholar.org/CorpusID:235458009](https://api.semanticscholar.org/CorpusID:235458009). [↗](https://api.semanticscholar.org/CorpusID:235458009)
40. Evan Hubinger, Chris van Merwijk, Vladimir Mikulik, Joar Skalse, and Scott Garrabrant. Risks from learned optimization in advanced machine learning systems. arXiv preprint arXiv:1906.01820, 2019. — [arXiv:1906.01820](https://arxiv.org/abs/1906.01820) [find](https://scholar.google.com/scholar?q=Evan+Hubinger%2C+Chris+van+Merwijk%2C+Vladimir+Mikulik%2C+Joar+Skalse%2C+and+Scott+Garrabrant%2E+Risks+from+learned+optimization+in+advanced+machine+learning+systems%2E+arXiv+preprint+arXiv%3A1906%2E01820%2C+2019%2E+%E2%80%94+%5Ba)
41. Joel Jang, Seungone Kim, Bill Yuchen Lin, Yizhong Wang, Jack Hessel, Luke S. Zettlemoyer, Hannaneh Hajishirzi, Yejin Choi, and Prithviraj Ammanabrolu. Personalized soups: Personalized large language model alignment via post-hoc parameter merging. ArXiv, abs/2310.11564, 2023. URL [https://api.semantic…](https://api.semantic…) [↗](https://api.semantic…)
42. Joel Jang, Seungone Kim, Bill Yuchen Lin, Yizhong Wang, Jack Hessel, Luke Zettlemoyer, Hannaneh Hajishirzi, Yejin Choi, and Prithviraj Ammanabrolu. Personalized soups: Personalized large language model alignment via post-hoc parameter merging. In Adaptive Foundation Models: Evolving AI for Personali… [find](https://scholar.google.com/scholar?q=Joel+Jang%2C+Seungone+Kim%2C+Bill+Yuchen+Lin%2C+Yizhong+Wang%2C+Jack+Hessel%2C+Luke+Zettlemoyer%2C+Hannaneh+Hajishirzi%2C+Yejin+Choi%2C+and+Prithviraj+Ammanabrolu%2E+Personalized+soups%3A+Personalized+large+language+mode)
43. Jiaming Ji, Tianyi Qiu, Boyuan Chen, Borong Zhang, Hantao Lou, Kaile Wang, Yawen Duan, Zhonghao He, Jiayi Zhou, Zhaowei Zhang, et al. [Ai alignment: A comprehensive survey](https://md.research.elamur.ai/free/en/papers/ji-2023-ai-alignment-comprehensive-survey/). arXiv preprint arXiv:2310.19852, 2023.
44. Guangyuan Jiang, Manjie Xu, Song-Chun Zhu, Wenjuan Han, Chi Zhang, and Yixin Zhu. Evaluating and inducing personality in pre-trained language models. Advances in Neural Information Processing Systems, 36, 2024. [find](https://scholar.google.com/scholar?q=Guangyuan+Jiang%2C+Manjie+Xu%2C+Song%2DChun+Zhu%2C+Wenjuan+Han%2C+Chi+Zhang%2C+and+Yixin+Zhu%2E+Evaluating+and+inducing+personality+in+pre%2Dtrained+language+models%2E+Advances+in+Neural+Information+Processing+Systems%2C)
45. Liwei Jiang, Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jenny Liang, Jesse Dodge, Keisuke Sakaguchi, Maxwell Forbes, Jon Borchardt, Saadia Gabriel, Yulia Tsvetkov, Oren Etzioni, Maarten Sap, Regina Rini, and Yejin Choi. Can machines learn morality? the delphi experiment, 2022. [find](https://scholar.google.com/scholar?q=Liwei+Jiang%2C+Jena+D%2E+Hwang%2C+Chandra+Bhagavatula%2C+Ronan+Le+Bras%2C+Jenny+Liang%2C+Jesse+Dodge%2C+Keisuke+Sakaguchi%2C+Maxwell+Forbes%2C+Jon+Borchardt%2C+Saadia+Gabriel%2C+Yulia+Tsvetkov%2C+Oren+Etzioni%2C+Maarten+Sap%2C+R)
46. John A Johnson. Measuring thirty facets of the five factor model with a 120-item public domain inventory: Development of the ipip-neo-120. Journal of research in personality, 51:78–89, 2014. [find](https://scholar.google.com/scholar?q=John+A+Johnson%2E+Measuring+thirty+facets+of+the+five+factor+model+with+a+120%2Ditem+public+domain+inventory%3A+Development+of+the+ipip%2Dneo%2D120%2E+Journal+of+research+in+personality%2C+51%3A78%E2%80%9389%2C+2014%2E)
47. Daniel N Jones and Delroy L Paulhus. Introducing the short dark triad (sd3) a brief measure of dark personality traits. Assessment, 21(1):28–41, 2014. [find](https://scholar.google.com/scholar?q=Daniel+N+Jones+and+Delroy+L+Paulhus%2E+Introducing+the+short+dark+triad+%28sd3%29+a+brief+measure+of+dark+personality+traits%2E+Assessment%2C+21%281%29%3A28%E2%80%9341%2C+2014%2E)
48. Diederik P. Kingma and Jimmy Ba. [Adam: A method for stochastic optimization](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/). CoRR, abs/1412.6980, 2014. URL [https://api.semanticscholar.org/CorpusID:](https://api.semanticscholar.org/CorpusID:) 6628106. [↗](https://api.semanticscholar.org/CorpusID:)
49. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). In Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (eds.), Advances in Neural Information Processing Systems, 2022. URL [https://openreview.net/forum?id=e…](https://openreview.net/forum?id=e…) [↗](https://openreview.net/forum?id=e…)
50. Jan Kulveit. Multi-agent predictive minds and ai alignment. [https://www.lesswrong.com/posts/3fkBWpE4f9nYbdf7E/](https://www.lesswrong.com/posts/3fkBWpE4f9nYbdf7E/) multi-agent-predictive-minds-and-ai-alignment, 2018. Accessed: 2024-04-25. [↗](https://www.lesswrong.com/posts/3fkBWpE4f9nYbdf7E/)
51. Harrison Lee, Samrat Phatale, Hassan Mansoor, Kellie Lu, Thomas Mesnard, Colton Bishop, Victor Carbune, and Abhinav Rastogi. Rlaif: Scaling reinforcement learning from human feedback with ai feedback. arXiv preprint arXiv:2309.00267, 2023. [find](https://scholar.google.com/scholar?q=Harrison+Lee%2C+Samrat+Phatale%2C+Hassan+Mansoor%2C+Kellie+Lu%2C+Thomas+Mesnard%2C+Colton+Bishop%2C+Victor+Carbune%2C+and+Abhinav+Rastogi%2E+Rlaif%3A+Scaling+reinforcement+learning+from+human+feedback+with+ai+feedback%2E)
52. Brian Lester, Rami Al-Rfou, and Noah Constant. [The power of scale for parameter-efficient prompt tuning](https://md.research.elamur.ai/free/en/papers/lester-2021-power-scale-parameter-efficient-prompt/), 2021. URL https://arxiv.org/abs/2104.08691. [↗](https://arxiv.org/abs/2104.08691)
53. Cheng Li, Ziang Leng, Chenxi Yan, Junyi Shen, Hao Wang, Weishi MI, Yaying Fei, Xiaoyang Feng, Song Yan, HaoSheng Wang, Linkang Zhan, Yaokai Jia, Pingyu Wu, and Haozhen Sun. [Chatharuhi: Reviving anime character in reality via large language model](https://md.research.elamur.ai/free/en/papers/li-2023-chatharuhi-reviving-anime-character-reality/), 2023.
54. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. [Inference-time intervention: Eliciting truthful answers from a language model](https://md.research.elamur.ai/free/en/papers/li-2023-inference-time-intervention-eliciting-truthful/). Advances in Neural Information Processing Systems, 36, 2024a.
55. Xinyu Li, Zachary C. Lipton, and Liu Leqi. Personalized language modeling from personalized human feedback. ArXiv, abs/2402.05133, 2024b. URL [https://api.semanticscholar.org/CorpusID:267547503](https://api.semanticscholar.org/CorpusID:267547503). — [arXiv:2402.05133](https://arxiv.org/abs/2402.05133) [↗](https://api.semanticscholar.org/CorpusID:267547503)
56. Bill Yuchen Lin, Abhilasha Ravichander, Ximing Lu, Nouha Dziri, Melanie Sclar, Khyathi Chandu, Chandra Bhagavatula, and Yejin Choi. [The unlocking spell on base llms: Rethinking alignment via in-context learning](https://md.research.elamur.ai/free/en/papers/lin-2023-unlocking-spell-base-llms-rethinking/), 2023.
57. Jianzhi Liu, Hexiang Gu, Tianyu Zheng, Liuyu Xiang, Huijia Wu, Jie Fu, and Zhaofeng He. Dynamic generation of personalities with large language models. arXiv preprint arXiv:2404.07084, 2024a. — [arXiv:2404.07084](https://arxiv.org/abs/2404.07084) [find](https://scholar.google.com/scholar?q=Jianzhi+Liu%2C+Hexiang+Gu%2C+Tianyu+Zheng%2C+Liuyu+Xiang%2C+Huijia+Wu%2C+Jie+Fu%2C+and+Zhaofeng+He%2E+Dynamic+generation+of+personalities+with+large+language+models%2E+arXiv+preprint+arXiv%3A2404%2E07084%2C+2024a%2E+%E2%80%94+%5BarXiv)
58. Tianlin Liu, Shangmin Guo, Leonardo Bianco, Daniele Calandriello, Quentin Berthet, Felipe Llinares-López, Jessica Hoffmann, Lucas Dixon, Michal Valko, and Mathieu Blondel. Decoding-time realignment of language models. ArXiv, abs/2402.02992, 2024b. URL https://api. semanticscholar.org/CorpusID:267411… — [arXiv:2402.02992](https://arxiv.org/abs/2402.02992) [find](https://scholar.google.com/scholar?q=Tianlin+Liu%2C+Shangmin+Guo%2C+Leonardo+Bianco%2C+Daniele+Calandriello%2C+Quentin+Berthet%2C+Felipe+Llinares%2DL%C3%B3pez%2C+Jessica+Hoffmann%2C+Lucas+Dixon%2C+Michal+Valko%2C+and+Mathieu+Blondel%2E+Decoding%2Dtime+realignment+of)
59. Xingzhou Lou, Junge Zhang, Jian Xie, Lifeng Liu, Dong Yan, and Kaiqi Huang. Spo: Multi-dimensional preference sequential alignment with implicit reward modeling. ArXiv, abs/2405.12739, 2024. URL [https://api.semanticscholar.org/CorpusID:](https://api.semanticscholar.org/CorpusID:) 269930031. — [arXiv:2405.12739](https://arxiv.org/abs/2405.12739) [↗](https://api.semanticscholar.org/CorpusID:)
60. Shengyu Mao, Ningyu Zhang, Xiaohan Wang, Mengru Wang, Yunzhi Yao, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. Editing personality for llms. arXiv preprint arXiv:2310.02168, 2023. — [arXiv:2310.02168](https://arxiv.org/abs/2310.02168) [find](https://scholar.google.com/scholar?q=Shengyu+Mao%2C+Ningyu+Zhang%2C+Xiaohan+Wang%2C+Mengru+Wang%2C+Yunzhi+Yao%2C+Yong+Jiang%2C+Pengjun+Xie%2C+Fei+Huang%2C+and+Huajun+Chen%2E+Editing+personality+for+llms%2E+arXiv+preprint+arXiv%3A2310%2E02168%2C+2023%2E+%E2%80%94+%5BarXiv%3A231)
61. Yash Mehta, Samin Fatehi, Amirmohammad Kazameini, Clemens Stachl, Erik Cambria, and Sauleh Eetemadi. Bottom-up and top-down: Predicting personality with psycholinguistic and language model features. In 2020 IEEE international conference on data mining (ICDM), pp. 1184–1189. [find](https://scholar.google.com/scholar?q=Yash+Mehta%2C+Samin+Fatehi%2C+Amirmohammad+Kazameini%2C+Clemens+Stachl%2C+Erik+Cambria%2C+and+Sauleh+Eetemadi%2E+Bottom%2Dup+and+top%2Ddown%3A+Predicting+personality+with+psycholinguistic+and+language+model+features%2E+I)
62. Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. Locating and editing factual associations in gpt. Advances in Neural Information Processing Systems, 35:17359–17372, 2022. [find](https://scholar.google.com/scholar?q=Kevin+Meng%2C+David+Bau%2C+Alex+Andonian%2C+and+Yonatan+Belinkov%2E+Locating+and+editing+factual+associations+in+gpt%2E+Advances+in+Neural+Information+Processing+Systems%2C+35%3A17359%E2%80%9317372%2C+2022%2E)
63. Man Tik Ng, Hui Tung Tse, Jen tse Huang, Jingjing Li, Wenxuan Wang, and Michael R. Lyu. How well can llms echo us? evaluating ai chatbots’ role-play ability with echo, 2024. [find](https://scholar.google.com/scholar?q=Man+Tik+Ng%2C+Hui+Tung+Tse%2C+Jen+tse+Huang%2C+Jingjing+Li%2C+Wenxuan+Wang%2C+and+Michael+R%2E+Lyu%2E+How+well+can+llms+echo+us%3F+evaluating+ai+chatbots%E2%80%99+role%2Dplay+ability+with+echo%2C+2024%2E)
64. Catherine Olsson, Nelson Elhage, Neel Nanda, Nicholas Joseph, Nova DasSarma, Tom Henighan, Ben Mann, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Dawn Drain, Deep Ganguli, Zac Hatfield-Dodds, Danny Hernandez, Scott Johnston, Andy Jones, Jackson Kernion, Liane Lovitt, Kamal Ndousse, Dario Amode… — [In-context Learning and Induction Heads](https://md.research.elamur.ai/free/en/papers/olsson-2022-context-learning-induction-heads/)
65. OpenAI. Hello gpt-4o. [https://openai.com/index/hello-gpt-4o](https://openai.com/index/hello-gpt-4o), 2024. Accessed: 2024-05-21. [↗](https://openai.com/index/hello-gpt-4o)
66. Keyu Pan and Yawen Zeng. [Do llms possess a personality? making the mbti test an amazing evaluation for large language models](https://md.research.elamur.ai/free/en/papers/pan-2023-llms-possess-personality-making-mbti/). arXiv preprint arXiv:2307.16180, 2023.
67. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and S… — [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/)
68. Rolf Pfeifer and Josh Bongard. How the body shapes the way we think: a new view of intelligence. MIT press, 2006. [find](https://scholar.google.com/scholar?q=Rolf+Pfeifer+and+Josh+Bongard%2E+How+the+body+shapes+the+way+we+think%3A+a+new+view+of+intelligence%2E+MIT+press%2C+2006%2E)
69. Liang Qiu, Yizhou Zhao, Jinchao Li, Pan Lu, Baolin Peng, Jianfeng Gao, and Song-Chun Zhu. Valuenet: A new dataset for human value driven dialogue system. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10):11183–11191, June 2022. ISSN 2159-5399. doi: 10. 1609/aaai.v36i10.21368. URL… — [doi:10.1609/aaai.v36i10.21368](https://doi.org/10.1609/aaai.v36i10.21368) [find](https://scholar.google.com/scholar?q=Liang+Qiu%2C+Yizhou+Zhao%2C+Jinchao+Li%2C+Pan+Lu%2C+Baolin+Peng%2C+Jianfeng+Gao%2C+and+Song%2DChun+Zhu%2E+Valuenet%3A+A+new+dataset+for+human+value+driven+dialogue+system%2E+Proceedings+of+the+AAAI+Conference+on+Artifici)
70. Alec Radford, Jeff Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. Language models are unsupervised multitask learners. 2019. URL [https://api.semanticscholar.org/CorpusID:160025533](https://api.semanticscholar.org/CorpusID:160025533). [↗](https://api.semanticscholar.org/CorpusID:160025533)
71. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/), 2023.
72. Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Matt Turner. Steering llama 2 via contrastive activation addition. arXiv preprint arXiv:2312.06681, 2023. [find](https://scholar.google.com/scholar?q=Nina+Rimsky%2C+Nick+Gabrieli%2C+Julian+Schulz%2C+Meg+Tong%2C+Evan+Hubinger%2C+and+Alexander+Matt+Turner%2E+Steering+llama+2+via+contrastive+activation+addition%2E+arXiv+preprint+arXiv%3A2312%2E06681%2C+2023%2E)
73. Sonia Roccas, Lilach Sagiv, Shalom H Schwartz, and Ariel Knafo. The big five personality factors and personal values. Personality and social psychology bulletin, 28(6):789–801, 2002. [find](https://scholar.google.com/scholar?q=Sonia+Roccas%2C+Lilach+Sagiv%2C+Shalom+H+Schwartz%2C+and+Ariel+Knafo%2E+The+big+five+personality+factors+and+personal+values%2E+Personality+and+social+psychology+bulletin%2C+28%286%29%3A789%E2%80%93801%2C+2002%2E)
74. Subhro Roy and Dan Roth. [Solving general arithmetic word problems](https://md.research.elamur.ai/free/en/papers/roy-2015-solving-general-arithmetic-word-problems/). arXiv: Computation and Language, 2016.
75. Alireza Salemi, Sheshera Mysore, Michael Bendersky, and Hamed Zamani. [Lamp: When large language models meet personalization](https://md.research.elamur.ai/free/en/papers/salemi-2024-lamp-when-large-language-models/), 2024.
76. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms, 2017. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+Proximal+policy+optimization+algorithms%2C+2017%2E)
77. Archit Sharma, Sedrick Keh, Eric Mitchell, Chelsea Finn, Kushal Arora, and Thomas Kollar. A critical evaluation of AI feedback for aligning large language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024. URL [https://openreview.net/forum?id=FZQYfmsmX9](https://openreview.net/forum?id=FZQYfmsmX9). [↗](https://openreview.net/forum?id=FZQYfmsmX9)
78. Tianhao Shen, Renren Jin, Yufei Huang, Chuang Liu, Weilong Dong, Zishan Guo, Xinwei Wu, Yan Liu, and Deyi Xiong. [Large language model alignment: A survey](https://md.research.elamur.ai/free/en/papers/shen-2023-large-language-model-alignment-survey/). arXiv preprint arXiv:2309.15025, 2023.
79. Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hanna Hajishirzi, Noah A. Smith, and Simon Shaolei Du. Decoding-time language model alignment with multiple objectives. ArXiv, abs/2406.18853, 2024. URL [https://api.semanticscholar.org/CorpusID:270764846](https://api.semanticscholar.org/CorpusID:270764846). — [arXiv:2406.18853](https://arxiv.org/abs/2406.18853) [↗](https://api.semanticscholar.org/CorpusID:270764846)
80. Irene Solaiman, Miles Brundage, Jack Clark, Amanda Askell, Ariel Herbert-Voss, Jeff Wu, Alec Radford, Gretchen Krueger, Jong Wook Kim, Sarah Kreps, et al. [Release strategies and the social impacts of language models](https://md.research.elamur.ai/free/en/papers/solaiman-2019-release-strategies-social-impacts-language/). arXiv preprint arXiv:1908.09203, 2019.
81. Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. Learning to summarize with human feedback. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (eds.), Advances in Neural Information Processing Systems,… [find](https://scholar.google.com/scholar?q=Nisan+Stiennon%2C+Long+Ouyang%2C+Jeffrey+Wu%2C+Daniel+Ziegler%2C+Ryan+Lowe%2C+Chelsea+Voss%2C+Alec+Radford%2C+Dario+Amodei%2C+and+Paul+F+Christiano%2E+Learning+to+summarize+with+human+feedback%2E+In+H%2E+Larochelle%2C+M%2E+Ran)
82. Jonathan Stray. Aligning ai optimization to community well-being. International Journal of Community Well-Being, 3(4):443–463, 2020. [find](https://scholar.google.com/scholar?q=Jonathan+Stray%2E+Aligning+ai+optimization+to+community+well%2Dbeing%2E+International+Journal+of+Community+Well%2DBeing%2C+3%284%29%3A443%E2%80%93463%2C+2020%2E)
83. Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V Le, Ed H Chi, Denny Zhou, et al. [Challenging big-bench tasks and whether chain-of-thought can solve them](https://md.research.elamur.ai/free/en/papers/suzgun-2023-challenging-big-bench-tasks-whether/). arXiv preprint arXiv:2210.09261, 2022.
84. Gokul Swamy, Christoph Dann, Rahul Kidambi, Zhiwei Steven Wu, and Alekh Agarwal. A minimaximalist approach to reinforcement learning from human feedback. arXiv preprint arXiv:2401.04056, 2024. — [arXiv:2401.04056](https://arxiv.org/abs/2401.04056) [find](https://scholar.google.com/scholar?q=Gokul+Swamy%2C+Christoph+Dann%2C+Rahul+Kidambi%2C+Zhiwei+Steven+Wu%2C+and+Alekh+Agarwal%2E+A+minimaximalist+approach+to+reinforcement+learning+from+human+feedback%2E+arXiv+preprint+arXiv%3A2401%2E04056%2C+2024%2E+%E2%80%94+%5BarXi)
85. Alon Talmor, Jonathan Herzig, Nicholas Lourie, and Jonathan Berant. [Commonsenseqa: A question answering challenge targeting commonsense knowledge](https://md.research.elamur.ai/free/en/papers/talmor-2019-commonsenseqa-question-answering-challenge-targeting/). north american chapter of the association for computational linguistics, 2018.
86. Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, et al. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295, 2024. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Thomas+Mesnard%2C+Cassidy+Hardin%2C+Robert+Dadashi%2C+Surya+Bhupatiraju%2C+Shreya+Pathak%2C+Laurent+Sifre%2C+Morgane+Rivi%C3%A8re%2C+Mihir+Sanjay+Kale%2C+Juliette+Love%2C+et+al%2E+Gemma%3A+Open+models+based+on+gemin)
87. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/), 2023a.
88. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
89. Jen tse Huang, Wenxuan Wang, Eric John Li, Man Ho LAM, Shujie Ren, Youliang Yuan, Wenxiang Jiao, Zhaopeng Tu, and Michael Lyu. On the humanity of conversational AI: Evaluating the psychological portrayal of LLMs. In The Twelfth International Conference on Learning Representations, 2024. URL https://… [find](https://scholar.google.com/scholar?q=Jen+tse+Huang%2C+Wenxuan+Wang%2C+Eric+John+Li%2C+Man+Ho+LAM%2C+Shujie+Ren%2C+Youliang+Yuan%2C+Wenxiang+Jiao%2C+Zhaopeng+Tu%2C+and+Michael+Lyu%2E+On+the+humanity+of+conversational+AI%3A+Evaluating+the+psychological+portra)
90. Alex Turner, Lisa Thiergart, David Udell, Gavin Leech, Ulisse Mini, and Monte MacDiarmid. Activation addition: Steering language models without optimization. arXiv preprint arXiv:2308.[10248, 2023](https://md.research.elamur.ai/free/en/papers/turner-2023-steering-language-models-activation-engineering/).
91. Aimee van Wynsberghe. Sustainable ai: Ai for sustainability and the sustainability of ai. AI and Ethics, 1:213 – 218, 2021. URL [https://api.semanticscholar.org/CorpusID:](https://api.semanticscholar.org/CorpusID:) 233944874. [↗](https://api.semanticscholar.org/CorpusID:)
92. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. [Attention is all you need](https://md.research.elamur.ai/free/en/papers/vaswani-2017-attention-all-need/). In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (eds.), Advances in Neural Information Processing Sy…
93. Paul Voigt and Axel Von dem Bussche. The eu general data protection regulation (gdpr). A Practical Guide, 1st Ed., Cham: Springer International Publishing, 10(3152676):10–5555, 2017. [find](https://scholar.google.com/scholar?q=Paul+Voigt+and+Axel+Von+dem+Bussche%2E+The+eu+general+data+protection+regulation+%28gdpr%29%2E+A+Practical+Guide%2C+1st+Ed%2E%2C+Cham%3A+Springer+International+Publishing%2C+10%283152676%29%3A10%E2%80%935555%2C+2017%2E)
94. Haoran Wang and Kai Shu. Trojan activation attack: Red-teaming large language models using activation steering for safety-alignment, 2024. URL https://arxiv.org/abs/2311.09433. — [arXiv:2311.09433](https://arxiv.org/abs/2311.09433) [↗](https://arxiv.org/abs/2311.09433)
95. Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, and Tong Zhang. [Arithmetic control of llms for diverse user preferences: Directional preference alignment with multi-objective rewards](https://md.research.elamur.ai/free/en/papers/wang-2024-arithmetic-control-llms-diverse-user/). ArXiv, abs/2402.18571, 2024a. URL https://api. semanticscholar.org/CorpusID:2680636…
96. Noah Wang, Z.y. Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhao Huang, Jie Fu, and Junran Peng. RoleLLM: Benchmarking, eliciting, and enhancing role-playing abilities of large language… [find](https://scholar.google.com/scholar?q=Noah+Wang%2C+Z%2Ey%2E+Peng%2C+Haoran+Que%2C+Jiaheng+Liu%2C+Wangchunshu+Zhou%2C+Yuhan+Wu%2C+Hongcheng+Guo%2C+Ruitong+Gan%2C+Zehao+Ni%2C+Jian+Yang%2C+Man+Zhang%2C+Zhaoxiang+Zhang%2C+Wanli+Ouyang%2C+Ke+Xu%2C+Wenhao+Huang%2C+Jie+Fu%2C+and+J)
97. Xintao Wang, Yunze Xiao, Jen-tse Huang, Siyu Yuan, Rui Xu, Haoran Guo, Quan Tu, Yaying Fei, Ziang Leng, Wei Wang, Jiangjie Chen, Cheng Li, and Yanghua Xiao. [InCharacter: Evaluating personality fidelity in role-playing agents through psychological interviews](https://md.research.elamur.ai/free/en/papers/wang-2024-incharacter-evaluating-personality-fidelity-role/). In Lun-Wei Ku, Andre Martins, and Vivek S…
98. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. [Emergent abilities of large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-emergent-abilities-large-language-models/). arXiv preprint arXiv:2206.07682, 2022a.
99. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed Chi, Quoc Le, and Denny Zhou. Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.[11903, 2022b](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/).
100. Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, and Jun Zhao. [Large language models are better reasoners with self-verification](https://md.research.elamur.ai/free/en/papers/weng-2023-large-language-models-are-better/). In Houda Bouamor, Juan Pino, and Kalika Bali (eds.), Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 2550…
101. Yixuan Weng, Shizhu He, Kang Liu, Shengping Liu, and Jun Zhao. Controllm: Crafting diverse personalities for language models. arXiv preprint arXiv:2402.10151, 2024a. — [arXiv:2402.10151](https://arxiv.org/abs/2402.10151) [find](https://scholar.google.com/scholar?q=Yixuan+Weng%2C+Shizhu+He%2C+Kang+Liu%2C+Shengping+Liu%2C+and+Jun+Zhao%2E+Controllm%3A+Crafting+diverse+personalities+for+language+models%2E+arXiv+preprint+arXiv%3A2402%2E10151%2C+2024a%2E+%E2%80%94+%5BarXiv%3A2402%2E10151%5D%28https%3A%2F%2Farxiv)
102. Yixuan Weng, Minjun Zhu, Fei Xia, Bin Li, Shizhu He, Kang Liu, and Jun Zhao. Mastering symbolic operations: Augmenting language models with compiled neural networks. In The Twelfth International Conference on Learning Representations, 2024b. URL [https://openreview.net/forum?id=9nsNyN0vox](https://openreview.net/forum?id=9nsNyN0vox). [↗](https://openreview.net/forum?id=9nsNyN0vox)
103. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Rémi Louf, Morgan Funtowicz, et al. Huggingface’s [transformers: State-of-the-art natural language processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/). arXiv preprint arXiv:1910.03771, 2019.
104. Zhengxuan Wu, Atticus Geiger, Aryaman Arora, Jing Huang, Zheng Wang, Noah D. Goodman, Christopher D. Manning, and Christopher Potts. pyvene: A library for understanding and improving PyTorch models via interventions. 2024a. URL arxiv.org/abs/2403.07809. [find](https://scholar.google.com/scholar?q=Zhengxuan+Wu%2C+Atticus+Geiger%2C+Aryaman+Arora%2C+Jing+Huang%2C+Zheng+Wang%2C+Noah+D%2E+Goodman%2C+Christopher+D%2E+Manning%2C+and+Christopher+Potts%2E+pyvene%3A+A+library+for+understanding+and+improving+PyTorch+models+vi)
105. Zhengxuan Wu, Atticus Geiger, Thomas Icard, Christopher Potts, and Noah Goodman. [Interpretability at scale: Identifying causal mechanisms in alpaca](https://md.research.elamur.ai/free/en/papers/wu-2023-interpretability-scale-identifying-causal-mechanisms/). Advances in Neural Information Processing Systems, 36, 2024b.
106. Guohai Xu, Jiayi Liu, Ming Yan, Haotian Xu, Jinghui Si, Zhuoran Zhou, Peng Yi, Xing Gao, Jitao Sang, Rong Zhang, Ji Zhang, Chao Peng, Fei Huang, and Jingren Zhou. [Cvalues: Measuring the values of chinese large language models from safety to responsibility](https://md.research.elamur.ai/free/en/papers/xu-2023-cvalues-measuring-values-chinese/), 2023.
107. Zhewei Yao, Reza Yazdani Aminabadi, Olatunji Ruwase, Samyam Rajbhandari, Xiaoxia Wu, Ammar Ahmad Awan, Jeff Rasley, Minjia Zhang, Conglong Li, Connor Holmes, Zhongzhu Zhou, Michael Wyatt, Molly Smith, Lev Kurilenko, Heyang Qin, Masahiro Tanaka, Shuai Che, Shuaiwen Leon Song, and Yuxiong He. Deepspee… [find](https://scholar.google.com/scholar?q=Zhewei+Yao%2C+Reza+Yazdani+Aminabadi%2C+Olatunji+Ruwase%2C+Samyam+Rajbhandari%2C+Xiaoxia+Wu%2C+Ammar+Ahmad+Awan%2C+Jeff+Rasley%2C+Minjia+Zhang%2C+Conglong+Li%2C+Connor+Holmes%2C+Zhongzhu+Zhou%2C+Michael+Wyatt%2C+Molly+Smith%2C)
108. Xiaoyan Yu, Tongxu Luo, Yifan Wei, Fangyu Lei, Yiming Huang, Hao Peng, and Liehuang Zhu. Neeko: Leveraging dynamic LoRA for efficient multi-character role-playing agent. In Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (eds.), Proceedings of the 2024 Conference on Empirical Methods in Natural La… [find](https://scholar.google.com/scholar?q=Xiaoyan+Yu%2C+Tongxu+Luo%2C+Yifan+Wei%2C+Fangyu+Lei%2C+Yiming+Huang%2C+Hao+Peng%2C+and+Liehuang+Zhu%2E+Neeko%3A+Leveraging+dynamic+LoRA+for+efficient+multi%2Dcharacter+role%2Dplaying+agent%2E+In+Yaser+Al%2DOnaizan%2C+Mohit+Ban)
109. Dun Zeng, Yong Dai, Pengyu Cheng, Tianhao Hu, Wanshun Chen, Nan Du, and Zenglin Xu. On diversified preferences of large language model alignment. ArXiv, abs/2312.07401, 2023. URL [https://api.semanticscholar.org/CorpusID:266174407](https://api.semanticscholar.org/CorpusID:266174407). [↗](https://api.semanticscholar.org/CorpusID:266174407)
110. Zhaowei Zhang, Ceyao Zhang, Nian Liu, Siyuan Qi, Ziqi Rong, Song-Chun Zhu, Shuguang Cui, and Yaodong Yang. Heterogeneous value alignment evaluation for large language models. In AAAI-2024 Workshop on Public Sector LLMs: Algorithmic and Sociotechnical Design, 2024. [find](https://scholar.google.com/scholar?q=Zhaowei+Zhang%2C+Ceyao+Zhang%2C+Nian+Liu%2C+Siyuan+Qi%2C+Ziqi+Rong%2C+Song%2DChun+Zhu%2C+Shuguang+Cui%2C+and+Yaodong+Yang%2E+Heterogeneous+value+alignment+evaluation+for+large+language+models%2E+In+AAAI%2D2024+Workshop+on+)
111. Chujie Zheng, Fan Yin, Hao Zhou, Fandong Meng, Jie Zhou, Kai-Wei Chang, Minlie Huang, and Nanyun Peng. On prompt-driven safeguarding for large language models. In ICML, 2024. URL [https://openreview.net/forum?id=ugxGpOEkox](https://openreview.net/forum?id=ugxGpOEkox). [↗](https://openreview.net/forum?id=ugxGpOEkox)
112. Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, Susan Zhang, Gargi Ghosh, Mike Lewis, Luke Zettlemoyer, and Omer Levy. Lima: Less is more for alignment, 2023a. [find](https://scholar.google.com/scholar?q=Chunting+Zhou%2C+Pengfei+Liu%2C+Puxin+Xu%2C+Srini+Iyer%2C+Jiao+Sun%2C+Yuning+Mao%2C+Xuezhe+Ma%2C+Avia+Efrat%2C+Ping+Yu%2C+Lili+Yu%2C+Susan+Zhang%2C+Gargi+Ghosh%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Omer+Levy%2E+Lima%3A+Less+is+mo)
113. Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. [Large language models are human-level prompt engineers](https://md.research.elamur.ai/free/en/papers/zhou-2022-large-language-models-human-level/), 2023b.
114. Yuchen Zhuang, Haotian Sun, Yue Yu, Rushi Qiang, Qifan Wang, Chao Zhang, and Bo Dai. Hydra: Model factorization framework for black-box llm personalization. ArXiv, abs/2406.02888, 2024. URL [https://api.semanticscholar.org/CorpusID:270257981](https://api.semanticscholar.org/CorpusID:270257981). — [arXiv:2406.02888](https://arxiv.org/abs/2406.02888) [↗](https://api.semanticscholar.org/CorpusID:270257981)

*Updated 30 October 2026*