---
title: "Multi-Attribute Steering of Language Models via Targeted"
description: "The authors propose MAT-Steer to address this. 55 references, cited by 10 papers here. Among them: 1."
authors: ["Duy Nguyen", "Archiki Prasad", "Elias Stengel-Eskin", "Mohit Bansal"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.1007/"
doi: "10.18653/v1/2025.acl-long.1007"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/nguyen-2025-multi-attribute-steering-language-models/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/nguyen-2025-multi-attribute-steering-language-models/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/8/) / Multi-Attribute Steering of Language Models via Targeted Intervention

# Multi-Attribute Steering of Language Models via Targeted Intervention

**Authors:** [Duy Nguyen](https://md.research.elamur.ai/free/en/authors/duy-nguyen/), [Archiki Prasad](https://md.research.elamur.ai/free/en/authors/archiki-prasad/), [Elias Stengel-Eskin](https://md.research.elamur.ai/free/en/authors/elias-stengel-eskin/) and [Mohit Bansal](https://md.research.elamur.ai/free/en/authors/mohit-bansal/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.1007/) · [PDF](https://aclanthology.org/2025.acl-long.1007.pdf) · [DOI 10.18653/v1/2025.acl-long.1007](https://doi.org/10.18653/v1/2025.acl-long.1007) · [OpenAlex](https://openalex.org/W4412945014)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [10](https://md.research.elamur.ai/free/en/papers/nguyen-2025-multi-attribute-steering-language-models/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Inference-time intervention (ITI) adjusts a large language model's behavior by adding steering vectors to its internal activations, with no weight updates. It handles one attribute well but struggles when several attributes must be satisfied at once and may conflict, for example being helpful without becoming biased. The authors propose MAT-Steer to address this. It learns one steering vector per attribute and pairs each vector with a sigmoid gating function. The gate decides, token by token, how strongly that vector should act, so tokens that are irrelevant to an attribute or already acceptable are left mostly untouched. Training uses an alignment objective that pulls the representations of undesirable responses toward those of desirable ones. Sparsity and orthogonality regularizers limit interference between attributes. On multiple-choice QA (TruthfulQA, Toxigen, BBQ) and generation (HelpSteer), MAT-Steer beats ITI methods such as LITO and fine-tuning baselines such as SFT and DPO. It also needs far less training data. This matters because it offers a cheap way to balance competing alignment goals without retraining.

## Key points
- On the QA benchmarks, MAT-Steer improves average accuracy by about 3%. On HelpSteer, it wins 55.82% of comparisons against the strongest ITI baseline, 67.59% against in-context learning, and 71.56% against standard ITI.
- In ablations on Llama-3.1-8B, TruthfulQA accuracy rises from 49.91 (base model) to 61.94 (full MAT-Steer). Removing any single component, such as positive-sample preservation, sparsity, orthogonality or normalization, lowers the score.
- It reaches the performance of the fine-tuning baselines with under 20% of their training data, without harming the model's general capabilities.
- Appendix experiments show gains on HH-RLHF and OBQA and across other model families such as Qwen 2.5. MAT-Steer can also be stacked on top of ICL or fine-tuning, and its win rate over baselines grows as more attributes are added.
- The code is released on GitHub (duykhuongnguyen/MAT-Steer).

*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 of North Carolina at Chapel Hill](https://md.research.elamur.ai/free/en/universities/university-of-north-carolina-at-chapel-hill/) — University, Chapel Hill, United States · 67 works · 16,474 citations

📚 Shelves (4): [🖥️ 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

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

## Cite

Cite as: Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin and Mohit Bansal. 2025. Multi-Attribute Steering of Language Models via Targeted Intervention. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{nguyen2025multi,
  title = {{Multi-Attribute Steering of Language Models via Targeted Intervention}},
  author = {Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin and Mohit Bansal},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.1007},
  url = {https://doi.org/10.18653/v1/2025.acl-long.1007}
}
```

- [← previous MEraser: An Effective Fingerprint Erasure Approach for Large Language Models](https://md.research.elamur.ai/free/en/papers/zhang-2025-meraser-effective-fingerprint-erasure-approach/)
- [next → Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer](https://md.research.elamur.ai/free/en/papers/du-2025-neural-parameter-search-slimmer-fine/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/8/)

## References

55 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, and 12 others. 202… [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+Nicholas+Joseph%2C+Saurav+Kadavath%2C+Jackson+Kernion%2C+Tom+Conerly%2C+)
3. Farima Fatahi Bayat, Xin Liu, H Jagadish, and Lu Wang. 2024. Enhanced language model truthfulness with learnable intervention and uncertainty expression. In Findings of the Association for Computational Linguistics ACL 2024, pages 12388–12400. [find](https://scholar.google.com/scholar?q=Farima+Fatahi+Bayat%2C+Xin+Liu%2C+H+Jagadish%2C+and+Lu+Wang%2E+2024%2E+Enhanced+language+model+truthfulness+with+learnable+intervention+and+uncertainty+expression%2E+In+Findings+of+the+Association+for+Computation)
4. Dan Biderman, Jacob Portes, Jose Javier Gonzalez Ortiz, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, Cody Blakeney, and John Patrick Cunningham. 2024. LoRA learns less and forgets less. Transactions on Machine Learning Research. Feature… [find](https://scholar.google.com/scholar?q=Dan+Biderman%2C+Jacob+Portes%2C+Jose+Javier+Gonzalez+Ortiz%2C+Mansheej+Paul%2C+Philip+Greengard%2C+Connor+Jennings%2C+Daniel+King%2C+Sam+Havens%2C+Vitaliy+Chiley%2C+Jonathan+Frankle%2C+Cody+Blakeney%2C+and+John+Patrick+Cun)
5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
6. Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, and Jingren Zhou. 2024. [How abilities in large language models are affected by supervised fine-tuning data composition](https://md.research.elamur.ai/free/en/papers/dong-2024-how-abilities-large-language-models/). In Proceedings of the 62nd Annual Meeting of the Association for…
7. Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar, Xianchao Wu, and Oleksii Kuchaiev. 2023. SteerLM: Attribute conditioned SFT as an (user-steerable) alternative to RLHF. In The 2023 Conference on Empirical Methods in Natural Language Processing. [find](https://scholar.google.com/scholar?q=Yi+Dong%2C+Zhilin+Wang%2C+Makesh+Narsimhan+Sreedhar%2C+Xianchao+Wu%2C+and+Oleksii+Kuchaiev%2E+2023%2E+SteerLM%3A+Attribute+conditioned+SFT+as+an+%28user%2Dsteerable%29+alternative+to+RLHF%2E+In+The+2023+Conference+on+Empir)
8. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
9. Arthur Gretton, Karsten M Borgwardt, Malte J Rasch, Bernhard Schölkopf, and Alexander Smola. 2012. A kernel two-sample test. The Journal of Machine Learning Research, 13(1):723–773. [find](https://scholar.google.com/scholar?q=Arthur+Gretton%2C+Karsten+M+Borgwardt%2C+Malte+J+Rasch%2C+Bernhard+Sch%C3%B6lkopf%2C+and+Alexander+Smola%2E+2012%2E+A+kernel+two%2Dsample+test%2E+The+Journal+of+Machine+Learning+Research%2C+13%281%29%3A723%E2%80%93773%2E)
10. Thomas Hartvigsen, Saadia Gabriel, Hamid Palangi, Maarten Sap, Dipankar Ray, and Ece Kamar. 2022. [ToxiGen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection](https://md.research.elamur.ai/free/en/papers/hartvigsen-2022-toxigen-large-scale-machine-generated/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1:…
11. Oskar John Hollinsworth, Curt Tigges, Atticus Geiger, and Neel Nanda. 2024. Language models linearly represent sentiment. In Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, pages 58–87, Miami, Florida, US. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Oskar+John+Hollinsworth%2C+Curt+Tigges%2C+Atticus+Geiger%2C+and+Neel+Nanda%2E+2024%2E+Language+models+linearly+represent+sentiment%2E+In+Proceedings+of+the+7th+BlackboxNLP+Workshop%3A+Analyzing+and+Interpreting+Neu)
12. Jakub Hoscilowicz, Adam Wiacek, Jan Chojnacki, Adam Cieslak, Leszek Michon, and Artur Janicki. 2024. Non-linear inference time intervention: Improving llm truthfulness. In Proc. [find](https://scholar.google.com/scholar?q=Jakub+Hoscilowicz%2C+Adam+Wiacek%2C+Jan+Chojnacki%2C+Adam+Cieslak%2C+Leszek+Michon%2C+and+Artur+Janicki%2E+2024%2E+Non%2Dlinear+inference+time+intervention%3A+Improving+llm+truthfulness%2E+In+Proc%2E)
13. Interspeech 2024, pages 4094–4098. [find](https://scholar.google.com/scholar?q=Interspeech+2024%2C+pages+4094%E2%80%934098%2E)
14. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. [LoRA: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In International Conference on Learning Representations.
15. Yue Huang, Lichao Sun, Haoran Wang, Siyuan Wu, Qihui Zhang, Yuan Li, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li, Hanchi Sun, Zhengliang Liu, Yixin Liu, Yijue Wang, Zhikun Zhang, Bertie Vidgen, Bhavya Kailkhura, Caiming Xiong, and 52 others. 2024. [Trustllm: Trustworthiness in large l…](https://md.research.elamur.ai/free/en/papers/huang-2024-trustllm-trustworthiness-large-language-models/)
16. Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, and 1 others. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088. [find](https://scholar.google.com/scholar?q=Albert+Q+Jiang%2C+Alexandre+Sablayrolles%2C+Antoine+Roux%2C+Arthur+Mensch%2C+Blanche+Savary%2C+Chris+Bamford%2C+Devendra+Singh+Chaplot%2C+Diego+de+las+Casas%2C+Emma+Bou+Hanna%2C+Florian+Bressand%2C+and+1+others%2E+2024%2E+Mi)
17. Gahyeon Kim, Sohee Kim, and Seokju Lee. 2024. Aapl: Adding attributes to prompt learning for vision-language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1572–1582. [find](https://scholar.google.com/scholar?q=Gahyeon+Kim%2C+Sohee+Kim%2C+and+Seokju+Lee%2E+2024%2E+Aapl%3A+Adding+attributes+to+prompt+learning+for+vision%2Dlanguage+models%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognitio)
18. Suhas Kotha, Jacob Mitchell Springer, and Aditi Raghunathan. 2024. [Understanding catastrophic forgetting in language models via implicit inference](https://md.research.elamur.ai/free/en/papers/kotha-2023-understanding-catastrophic-forgetting-language-models/). In The Twelfth International Conference on Learning Representations.
19. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. 2024. [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.
20. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4582–… [find](https://scholar.google.com/scholar?q=Xiang+Lisa+Li+and+Percy+Liang%2E+2021%2E+Prefix%2Dtuning%3A+Optimizing+continuous+prompts+for+generation%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+11t)
21. Zhizhong Li and Derek Hoiem. 2017. Learning without forgetting. IEEE transactions on pattern analysis and machine intelligence, 40(12):2935–2947. [find](https://scholar.google.com/scholar?q=Zhizhong+Li+and+Derek+Hoiem%2E+2017%2E+Learning+without+forgetting%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence%2C+40%2812%29%3A2935%E2%80%932947%2E)
22. Sheng Liu, Haotian Ye, Lei Xing, and James Y Zou. 2024b. In-context vectors: Making in context learning more effective and controllable through latent space steering. In Forty-first International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Sheng+Liu%2C+Haotian+Ye%2C+Lei+Xing%2C+and+James+Y+Zou%2E+2024b%2E+In%2Dcontext+vectors%3A+Making+in+context+learning+more+effective+and+controllable+through+latent+space+steering%2E+In+Forty%2Dfirst+International+Conf)
23. Yajing Liu, Yuning Lu, Hao Liu, Yaozu An, Zhuoran Xu, Zhuokun Yao, Baofeng Zhang, Zhiwei Xiong, and Chenguang Gui. 2023. Hierarchical prompt learning for multi-task learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10888–10898. [find](https://scholar.google.com/scholar?q=Yajing+Liu%2C+Yuning+Lu%2C+Hao+Liu%2C+Yaozu+An%2C+Zhuoran+Xu%2C+Zhuokun+Yao%2C+Baofeng+Zhang%2C+Zhiwei+Xiong%2C+and+Chenguang+Gui%2E+2023%2E+Hierarchical+prompt+learning+for+multi%2Dtask+learning%2E+In+Proceedings+of+the+IEE)
24. Varvara Logacheva, Daryna Dementieva, Sergey Ustyantsev, Daniil Moskovskiy, David Dale, Irina Krotova, Nikita Semenov, and Alexander Panchenko. 2022. [ParaDetox: Detoxification with parallel data](https://md.research.elamur.ai/free/en/papers/logacheva-2022-paradetox-detoxification-parallel-data/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo…
25. David Lopez-Paz and Marc’Aurelio Ranzato. 2017. Gradient episodic memory for continual learning. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=David+Lopez%2DPaz+and+Marc%E2%80%99Aurelio+Ranzato%2E+2017%2E+Gradient+episodic+memory+for+continual+learning%2E+Advances+in+neural+information+processing+systems%2C+30%2E)
26. Todor Mihaylov, Peter Clark, Tushar Khot, and Ashish Sabharwal. 2018. Can a suit of armor conduct electricity? a new dataset for open book question answering. In EMNLP. [find](https://scholar.google.com/scholar?q=Todor+Mihaylov%2C+Peter+Clark%2C+Tushar+Khot%2C+and+Ashish+Sabharwal%2E+2018%2E+Can+a+suit+of+armor+conduct+electricity%3F+a+new+dataset+for+open+book+question+answering%2E+In+EMNLP%2E)
27. Yifei Ming, Senthil Purushwalkam, Shrey Pandit, Zixuan Ke, Xuan-Phi Nguyen, Caiming Xiong, and Shafiq Joty. 2025. Faitheval: Can your language model stay faithful to context, even if ”the moon is made of marshmallows”. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yifei+Ming%2C+Senthil+Purushwalkam%2C+Shrey+Pandit%2C+Zixuan+Ke%2C+Xuan%2DPhi+Nguyen%2C+Caiming+Xiong%2C+and+Shafiq+Joty%2E+2025%2E+Faitheval%3A+Can+your+language+model+stay+faithful+to+context%2C+even+if+%E2%80%9Dthe+moon+is+made)
28. Sidharth Mudgal, Jong Lee, Harish Ganapathy, YaGuang Li, Tao Wang, Yanping Huang, Zhifeng Chen, Heng-Tze Cheng, Michael Collins, Trevor Strohman, Jilin Chen, Alex Beutel, and Ahmad Beirami. 2024. Controlled decoding from language models. In ICML. [find](https://scholar.google.com/scholar?q=Sidharth+Mudgal%2C+Jong+Lee%2C+Harish+Ganapathy%2C+YaGuang+Li%2C+Tao+Wang%2C+Yanping+Huang%2C+Zhifeng+Chen%2C+Heng%2DTze+Cheng%2C+Michael+Collins%2C+Trevor+Strohman%2C+Jilin+Chen%2C+Alex+Beutel%2C+and+Ahmad+Beirami%2E+2024%2E+Cont)
29. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744.
30. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. [TruthfulQA: Measuring how models mimic human falsehoods](https://md.research.elamur.ai/free/en/papers/lin-2022-truthfulqa-measuring-how-models-mimic/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3214–3252, Dublin, Ireland. Association for Computational Linguistics…
31. Alicia Parrish, Angelica Chen, Nikita Nangia, Vishakh Padmakumar, Jason Phang, Jana Thompson, Phu Mon Htut, and Samuel Bowman. 2022. [BBQ: A hand-built bias benchmark for question answering](https://md.research.elamur.ai/free/en/papers/parrish-2022-bbq-hand-built-bias-benchmark/). In Findings of the Association for Computational Linguistics: ACL 2022, pages 2086–2105, Dublin, Ireland. Asso…
32. Bingchang Liu, Chaoyu Chen, Zi Gong, Cong Liao, Huan Wang, Zhichao Lei, Ming Liang, Dajun Chen, Min Shen, Hailian Zhou, and 1 others. 2024a. Mftcoder: Boosting code llms with multitask fine-tuning. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5430–54… [find](https://scholar.google.com/scholar?q=Bingchang+Liu%2C+Chaoyu+Chen%2C+Zi+Gong%2C+Cong+Liao%2C+Huan+Wang%2C+Zhichao+Lei%2C+Ming+Liang%2C+Dajun+Chen%2C+Min+Shen%2C+Hailian+Zhou%2C+and+1+others%2E+2024a%2E+Mftcoder%3A+Boosting+code+llms+with+multitask+fine%2Dtuning%2E+In)
33. Van-Cuong Pham and Thien Huu Nguyen. 2024. Householder pseudo-rotation: A novel approach to activation editing in LLMs with direction-magnitude perspective. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 13737–13751, Miami, Florida, USA. Association… [find](https://scholar.google.com/scholar?q=Van%2DCuong+Pham+and+Thien+Huu+Nguyen%2E+2024%2E+Householder+pseudo%2Drotation%3A+A+novel+approach+to+activation+editing+in+LLMs+with+direction%2Dmagnitude+perspective%2E+In+Proceedings+of+the+2024+Conference+on+Em)
34. Archiki Prasad, Peter Hase, Xiang Zhou, and Mohit Bansal. 2023. [GrIPS: Gradient-free, edit-based instruction search for prompting large language models](https://md.research.elamur.ai/free/en/papers/prasad-2023-grips-gradient-free-edit-based/). In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3845–3864, Dubrovnik, Croatia…
35. Guanghui Qin and Jason Eisner. 2021. [Learning how to ask: Querying LMs with mixtures of soft prompts](https://md.research.elamur.ai/free/en/papers/qin-2021-learning-ask-querying-lms-mixtures/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5203–5212, Online. Association for Computatio…
36. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2024. [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/). Advances in Neural Information Processing Systems, 36.
37. Alexandre Rame, Guillaume Couairon, Corentin Dancette, Jean-Baptiste Gaya, Mustafa Shukor, Laure Soulier, and Matthieu Cord. 2024. Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Alexandre+Rame%2C+Guillaume+Couairon%2C+Corentin+Dancette%2C+Jean%2DBaptiste+Gaya%2C+Mustafa+Shukor%2C+Laure+Soulier%2C+and+Matthieu+Cord%2E+2024%2E+Rewarded+soups%3A+towards+pareto%2Doptimal+alignment+by+interpolating+wei)
38. Nina Rimsky, Nick Gabrieli, Julian Schulz, Meg Tong, Evan Hubinger, and Alexander Turner. 2024. Steering llama 2 via contrastive activation addition. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15504–15522, Bangkok, Thaila… [find](https://scholar.google.com/scholar?q=Nina+Rimsky%2C+Nick+Gabrieli%2C+Julian+Schulz%2C+Meg+Tong%2C+Evan+Hubinger%2C+and+Alexander+Turner%2E+2024%2E+Steering+llama+2+via+contrastive+activation+addition%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+A)
39. Omar Shaikh, Hongxin Zhang, William Held, Michael Bernstein, and Diyi Yang. 2023. [On second thought, let‘s not think step by step!](https://md.research.elamur.ai/free/en/papers/shaikh-2023-second-thought-let-s-not/) bias and toxicity in zero-shot reasoning. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4454–…
40. Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu, Hannaneh Hajishirzi, Noah A. Smith, and Simon Shaolei Du. 2024. Decoding-time language model alignment with multiple objectives. In ICML 2024 Workshop on Theoretical Foundations of Foundation Models. [find](https://scholar.google.com/scholar?q=Ruizhe+Shi%2C+Yifang+Chen%2C+Yushi+Hu%2C+Alisa+Liu%2C+Hannaneh+Hajishirzi%2C+Noah+A%2E+Smith%2C+and+Simon+Shaolei+Du%2E+2024%2E+Decoding%2Dtime+language+model+alignment+with+multiple+objectives%2E+In+ICML+2024+Workshop+on+)
41. Daniel Chee Hian Tan, David Chanin, Aengus Lynch, Brooks Paige, Dimitrios Kanoulas, Adrià Garriga-Alonso, and Robert Kirk. 2024. Analysing the generalisation and reliability of steering vectors. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Daniel+Chee+Hian+Tan%2C+David+Chanin%2C+Aengus+Lynch%2C+Brooks+Paige%2C+Dimitrios+Kanoulas%2C+Adri%C3%A0+Garriga%2DAlonso%2C+and+Robert+Kirk%2E+2024%2E+Analysing+the+generalisation+and+reliability+of+steering+vectors%2E+In+Th)
42. Gemini Team, Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M. Dai, Anja Hauth, Katie Millican, David Silver, Melvin Johnson, Ioannis Antonoglou, Julian Schrittwieser, Amelia Glaese, Jilin Chen, Emily Pitler, Timothy Lillicrap, Angeliki Lazari… — [Gemini: A Family of Highly Capable Multimodal Models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/)
43. Qwen Team. 2024. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
44. Aman Singh Thakur, Kartik Choudhary, Venkat Srinik Ramayapally, Sankaran Vaidyanathan, and Dieuwke Hupkes. 2024. Judging the judges: Evaluating alignment and vulnerabilities in llms-as-judges. arXiv preprint arXiv:2406.12624. [find](https://scholar.google.com/scholar?q=Aman+Singh+Thakur%2C+Kartik+Choudhary%2C+Venkat+Srinik+Ramayapally%2C+Sankaran+Vaidyanathan%2C+and+Dieuwke+Hupkes%2E+2024%2E+Judging+the+judges%3A+Evaluating+alignment+and+vulnerabilities+in+llms%2Das%2Djudges%2E+arXiv+p)
45. Xinyu Tian, Shu Zou, Zhaoyuan Yang, and Jing Zhang. 2024. Argue: Attribute-guided prompt tuning for vision-language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 28578–28587. [find](https://scholar.google.com/scholar?q=Xinyu+Tian%2C+Shu+Zou%2C+Zhaoyuan+Yang%2C+and+Jing+Zhang%2E+2024%2E+Argue%3A+Attribute%2Dguided+prompt+tuning+for+vision%2Dlanguage+models%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Rec)
46. Alexander Matt Turner, Lisa Thiergart, Gavin Leech, David Udell, Juan J. Vazquez, Ulisse Mini, and Monte MacDiarmid. 2024. [Steering language models with activation engineering](https://md.research.elamur.ai/free/en/papers/turner-2023-steering-language-models-activation-engineering/). Preprint, arXiv:2308.10248.
47. Teun van der Weij, Massimo Poesio, and Nandi Schoots. 2024. Extending activation steering to broad skills and multiple behaviours. arXiv preprint arXiv:2403.05767. — [arXiv:2403.05767](https://arxiv.org/abs/2403.05767) [find](https://scholar.google.com/scholar?q=Teun+van+der+Weij%2C+Massimo+Poesio%2C+and+Nandi+Schoots%2E+2024%2E+Extending+activation+steering+to+broad+skills+and+multiple+behaviours%2E+arXiv+preprint+arXiv%3A2403%2E05767%2E+%E2%80%94+%5BarXiv%3A2403%2E05767%5D%28https%3A%2F%2Farxiv%2Eo)
48. Haoxiang Wang, Yong Lin, Wei Xiong, Rui Yang, Shizhe Diao, Shuang Qiu, Han Zhao, and Tong Zhang. 2024a. [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/). In Proceedings of the 62nd Annual Meeting of the Association for Computation…
49. Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, and Tong Zhang. 2024b. [Interpretable preferences via multi-objective reward modeling and mixture-of-experts](https://md.research.elamur.ai/free/en/papers/wang-2024-interpretable-preferences-multi-objective-reward/). In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10582– 10592, Miami, Florida, USA. Association for Computatio…
50. Zhilin Wang, Yi Dong, Olivier Delalleau, Jiaqi Zeng, Gerald Shen, Daniel Egert, Jimmy J. Zhang, Makesh Narsimhan Sreedhar, and Oleksii Kuchaiev. 2024c. Helpsteer 2: Open-source dataset for training top-performing reward models. In The Thirty-eight Conference on Neural Information Processing Systems… [find](https://scholar.google.com/scholar?q=Zhilin+Wang%2C+Yi+Dong%2C+Olivier+Delalleau%2C+Jiaqi+Zeng%2C+Gerald+Shen%2C+Daniel+Egert%2C+Jimmy+J%2E+Zhang%2C+Makesh+Narsimhan+Sreedhar%2C+and+Oleksii+Kuchaiev%2E+2024c%2E+Helpsteer+2%3A+Open%2Dsource+dataset+for+training+to)
51. Zhilin Wang, Yi Dong, Jiaqi Zeng, Virginia Adams, Makesh Narsimhan Sreedhar, Daniel Egert, Olivier Delalleau, Jane Scowcroft, Neel Kant, Aidan Swope, and Oleksii Kuchaiev. 2024d. [HelpSteer: Multi-attribute helpfulness dataset for SteerLM](https://md.research.elamur.ai/free/en/papers/wang-2024-helpsteer-multi-attribute-helpfulness-dataset/). In Proceedings of the 2024 Conference of the North American C…
52. Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and 1 others. 2022. [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://md.research.elamur.ai/free/en/papers/wortsman-2022-model-soups-averaging-weights-multiple/)…
53. Zeqiu Wu, Yushi Hu, Weijia Shi, Nouha Dziri, Alane Suhr, Prithviraj Ammanabrolu, Noah A. Smith, Mari Ostendorf, and Hannaneh Hajishirzi. 2023. [Fine-grained human feedback gives better rewards for language model training](https://md.research.elamur.ai/free/en/papers/wu-2023-fine-grained-human-feedback-gives/). In Thirty-seventh Conference on Neural Information Processing Systems.
54. Zhengxuan Wu, Aryaman Arora, Zheng Wang, Atticus Geiger, Dan Jurafsky, Christopher D Manning, and Christopher Potts. 2024. ReFT: Representation fine-tuning for language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Zhengxuan+Wu%2C+Aryaman+Arora%2C+Zheng+Wang%2C+Atticus+Geiger%2C+Dan+Jurafsky%2C+Christopher+D+Manning%2C+and+Christopher+Potts%2E+2024%2E+ReFT%3A+Representation+fine%2Dtuning+for+language+models%2E+In+The+Thirty%2Deighth+An)
55. Bowen Xu, Shaoyu Wu, Kai Liu, and Lulu Hu. 2025. Mixture-of-instructions: Aligning large language models via mixture prompting. Preprint, arXiv:2404.18410. — [arXiv:2404.18410](https://arxiv.org/abs/2404.18410) [find](https://scholar.google.com/scholar?q=Bowen+Xu%2C+Shaoyu+Wu%2C+Kai+Liu%2C+and+Lulu+Hu%2E+2025%2E+Mixture%2Dof%2Dinstructions%3A+Aligning+large+language+models+via+mixture+prompting%2E+Preprint%2C+arXiv%3A2404%2E18410%2E+%E2%80%94+%5BarXiv%3A2404%2E18410%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2)

*Updated 31 October 2026*