---
title: "Persona-DB — paper by Sun et al. (2025) — summary and ideas"
description: "The paper addresses context efficiency in retrieval-augmented LLM personalization: how to keep… 35 references, cited by 28 papers here."
authors: ["Chenkai Sun", "Ke Yang", "Revanth Gangi Reddy", "Yi Fung", "Hou Pong Chan", "Kevin Small", "ChengXiang Zhai", "Heng Ji"]
year: 2025
venue: "Proceedings of the 31st International Conference on Computational Linguistics"
source: "https://aclanthology.org/2025.coling-main.20/"
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/sun-2025-persona-db-efficient-large-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2025-persona-db-efficient-large-language/)

[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/3/) / Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement

# Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement

**Authors:** [Chenkai Sun](https://md.research.elamur.ai/free/en/authors/chenkai-sun/), [Ke Yang](https://md.research.elamur.ai/free/en/authors/ke-yang/), Revanth Gangi Reddy, [Yi Fung](https://md.research.elamur.ai/free/en/authors/yi-fung/), [Hou Pong Chan](https://md.research.elamur.ai/free/en/authors/hou-pong-chan/), Kevin Small, [ChengXiang Zhai](https://md.research.elamur.ai/free/en/authors/chengxiang-zhai/) and [Heng Ji](https://md.research.elamur.ai/free/en/authors/heng-ji/) · **Year:** 2025 · **Venue:** [Proceedings of the 31st International Conference on Computational Linguistics](https://md.research.elamur.ai/free/en/venues/coling/) ([COLING 2025](https://md.research.elamur.ai/free/en/venues/coling/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.coling-main.20/) · [PDF](https://aclanthology.org/2025.coling-main.20.pdf) · [OpenAlex](https://openalex.org/W4392011869)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · [28](https://md.research.elamur.ai/free/en/papers/sun-2025-persona-db-efficient-large-language/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper addresses context efficiency in retrieval-augmented LLM personalization: how to keep predictions of a user's reactions accurate while placing fewer retrieved items into the prompt. Earlier work mostly improved the retriever and relied on raw, scattered interaction logs or summaries. The authors focus instead on how the user database is represented. Their framework, Persona-DB, has two parts. First, a hierarchical refinement step uses an instruction-tuned LLM to turn raw history into distilled facts and then into more abstract, induced traits such as values and ideology. Second, a collaborative refinement step, inspired by collaborative filtering, links each user to similar users through shared persona keys. This lets the system fill gaps in sparse profiles.

On news response forecasting and OpinionQA, Persona-DB beats baselines across retrieval sizes. It stays stronger even when its retrieval budget is ten times smaller. It also improves results for cold-start users. This matters for users with long histories, sparse data, or LLMs with short context windows.

## Key points
- The database hierarchy has four layers: History (raw records), Distilled Persona (DP), Induced Persona (IP), and a Cache layer used to match and JOIN related users' databases. The same LLM handles both the refinement and the downstream prediction.
- Evaluation covers two tasks:
  - Response Forecasting for News Media (Sun et al., 2023), predicting how users react to news messages.
  - OpinionQA (Santurkar et al., 2023), predicting individual survey answers.
- Persona-DB outperforms baselines even when its maximal retrieval size is 10× smaller than the baseline's.
- For users with extremely sparse data (cold start), the gain exceeds 10%, for example about 11% on the correlation metric.
- A heatmap analysis of Pearson correlation shows two trends:
  - With larger retrieval budgets, a higher share of collaborative items improves results.
  - With very small budgets, the user's own data matters most, and relying heavily on other users' data can hurt.
- Code is available at github.com/chenkaisun/Persona-DB. Building the database requires a one-time LLM preprocessing cost.

*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 Illinois Urbana-Champaign](https://md.research.elamur.ai/free/en/universities/university-of-illinois-urbana-champaign/) — University, Urbana, United States · 184 works · 69,372 citations

📚 Shelves (5): [🖥️ 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 · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

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

## Cite

Cite as: Chenkai Sun, Ke Yang, Revanth Gangi Reddy, Yi Fung, Hou Pong Chan, Kevin Small, ChengXiang Zhai and Heng Ji. 2025. Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement. Proceedings of the 31st International Conference on Computational Linguistics.

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

```bibtex
@inproceedings{sun2025persona,
  title = {{Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement}},
  author = {Chenkai Sun, Ke Yang, Revanth Gangi Reddy, Yi Fung, Hou Pong Chan, Kevin Small, ChengXiang Zhai and Heng Ji},
  booktitle = {Proceedings of the 31st International Conference on Computational Linguistics},
  year = {2025},
  url = {https://aclanthology.org/2025.coling-main.20/}
}
```

- [← previous PaSa: An LLM Agent for Comprehensive Academic Paper Search](https://md.research.elamur.ai/free/en/papers/he-2025-pasa-llm-agent-comprehensive-academic/)
- [next → Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling](https://md.research.elamur.ai/free/en/papers/wan-2025-reasoning-aware-self-consistency-leveraging/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

35 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Icek Ajzen. 1991. The theory of planned behavior. Organizational Behavior and Human Decision Processes. [find](https://scholar.google.com/scholar?q=Icek+Ajzen%2E+1991%2E+The+theory+of+planned+behavior%2E+Organizational+Behavior+and+Human+Decision+Processes%2E)
2. Akari Asai, Timo Schick, Patrick Lewis, Xilun Chen, Our personalization approach involves storing and Gautier Izacard, Sebastian Riedel, Hannaneh Ha-retrieving information about user preferences and jishirzi, and Wen-tau Yih. 2022. Task-aware retrieval personalities, which requires careful safety pr… — [arXiv:2211.09260](https://arxiv.org/abs/2211.09260) [find](https://scholar.google.com/scholar?q=Akari+Asai%2C+Timo+Schick%2C+Patrick+Lewis%2C+Xilun+Chen%2C+Our+personalization+approach+involves+storing+and+Gautier+Izacard%2C+Sebastian+Riedel%2C+Hannaneh+Ha%2Dretrieving+information+about+user+preferences+and+j)
3. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416. [find](https://scholar.google.com/scholar?q=Hyung+Won+Chung%2C+Le+Hou%2C+Shayne+Longpre%2C+Barret+Zoph%2C+Yi+Tay%2C+William+Fedus%2C+Yunxuan+Li%2C+Xuezhi+Wang%2C+Mostafa+Dehghani%2C+Siddhartha+Brahma%2C+et+al%2E+2022%2E+Scaling+instruction%2Dfinetuned+language+models%2E+a)
4. Yi Fung, Tuhin Chakrabarty, Hao Guo, Owen Rambow, Smaranda Muresan, and Heng Ji. 2023. NORM-SAGE: Multi-lingual multi-cultural norm discovery from conversations on-the-fly. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15217–15230, Singapore. Associ… [find](https://scholar.google.com/scholar?q=Yi+Fung%2C+Tuhin+Chakrabarty%2C+Hao+Guo%2C+Owen+Rambow%2C+Smaranda+Muresan%2C+and+Heng+Ji%2E+2023%2E+NORM%2DSAGE%3A+Multi%2Dlingual+multi%2Dcultural+norm+discovery+from+conversations+on%2Dthe%2Dfly%2E+In+Proceedings+of+the+2023+)
5. Yi Fung, Ruining Zhao, Jae Doo, Chenkai Sun, and Heng Ji. 2024. [Massively multi-cultural knowledge acquisition & lm benchmarking](https://md.research.elamur.ai/free/en/papers/fung-2024-massively-multi-cultural-knowledge-acquisition/). Preprint, arXiv:2402.09369.
6. Tao Ge, Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, and Dong Yu. 2024. [Scaling synthetic data creation with 1,000,000,000 personas](https://md.research.elamur.ai/free/en/papers/ge-2024-scaling-synthetic-data-creation-1/). arXiv preprint arXiv:2406.20094.
7. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Mingwei Chang. 2020. [Retrieval augmented language model pre-training](https://md.research.elamur.ai/free/en/papers/guu-2020-realm-retrieval-augmented-language-model/). In International conference on machine learning, pages 3929–3938. PMLR.
8. Chi Han, Jialiang Xu, Manling Li, Yi Fung, Chenkai Sun, Nan Jiang, Tarek Abdelzaher, and Heng Ji. 2023. Lm-switch: Lightweight language model conditioning in word embedding space. arXiv preprint arXiv:2305.12798. — [arXiv:2305.12798](https://arxiv.org/abs/2305.12798) [find](https://scholar.google.com/scholar?q=Chi+Han%2C+Jialiang+Xu%2C+Manling+Li%2C+Yi+Fung%2C+Chenkai+Sun%2C+Nan+Jiang%2C+Tarek+Abdelzaher%2C+and+Heng+Ji%2E+2023%2E+Lm%2Dswitch%3A+Lightweight+language+model+conditioning+in+word+embedding+space%2E+arXiv+preprint+arXiv)
9. EunJeong Hwang, Bodhisattwa Prasad Majumder, and Niket Tandon. 2023. [Aligning language models to user opinions](https://md.research.elamur.ai/free/en/papers/hwang-2023-aligning-language-models-user-opinions/). CoRR, abs/2305.14929.
10. Milton King and Paul Cook. 2020. Evaluating approaches to personalizing language models. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 2461–2469. [find](https://scholar.google.com/scholar?q=Milton+King+and+Paul+Cook%2E+2020%2E+Evaluating+approaches+to+personalizing+language+models%2E+In+Proceedings+of+the+Twelfth+Language+Resources+and+Evaluation+Conference%2C+pages+2461%E2%80%932469%2E)
11. Hannah Rose Kirk, Bertie Vidgen, Paul Röttger, and Scott A Hale. 2023. [Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback](https://md.research.elamur.ai/free/en/papers/kirk-2023-personalisation-within-bounds-risk-taxonomy/). arXiv preprint arXiv:2303.05453.
12. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in Neural Information Processing Systems, 33:9459–9474.
13. Junyi Li, Ninareh Mehrabi, Charith Peris, Palash Goyal, Kai-Wei Chang, Aram Galstyan, Richard Zemel, and Rahul Gupta. 2023a. On the steerability of large language models toward data-driven personas. arXiv preprint arXiv:2311.04978. [find](https://scholar.google.com/scholar?q=Junyi+Li%2C+Ninareh+Mehrabi%2C+Charith+Peris%2C+Palash+Goyal%2C+Kai%2DWei+Chang%2C+Aram+Galstyan%2C+Richard+Zemel%2C+and+Rahul+Gupta%2E+2023a%2E+On+the+steerability+of+large+language+models+toward+data%2Ddriven+personas%2E+a)
14. Sha Li, Chi Han, Pengfei Yu, Carl Edwards, Manling Li, Xingyao Wang, Yi Fung, Charles Yu, Joel Tetreault, Eduard Hovy, and Heng Ji. 2023b. Defining a new NLP playground. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11932–11951, Singapore. Association for Computatio… [find](https://scholar.google.com/scholar?q=Sha+Li%2C+Chi+Han%2C+Pengfei+Yu%2C+Carl+Edwards%2C+Manling+Li%2C+Xingyao+Wang%2C+Yi+Fung%2C+Charles+Yu%2C+Joel+Tetreault%2C+Eduard+Hovy%2C+and+Heng+Ji%2E+2023b%2E+Defining+a+new+NLP+playground%2E+In+Findings+of+the+Association)
15. Shengyu Mao, Ningyu Zhang, Xiaohan Wang, Mengru Wang, Yunzhi Yao, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. 2023. Editing personality for llms. arXiv preprint arXiv:2310.02168. — [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+2023%2E+Editing+personality+for+llms%2E+arXiv+preprint+arXiv%3A2310%2E02168%2E+%E2%80%94+%5BarXiv%3A231)
16. Colleen McClain, Regina Widjaya, Gonzalo Rivero, and Aaron Smith. 2021. The behaviors and attitudes of us adults on twitter. [find](https://scholar.google.com/scholar?q=Colleen+McClain%2C+Regina+Widjaya%2C+Gonzalo+Rivero%2C+and+Aaron+Smith%2E+2021%2E+The+behaviors+and+attitudes+of+us+adults+on+twitter%2E)
17. Fatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, and Dimitrios Dimitriadis. 2022. Useridentifier: Implicit user representations for simple and effective personalized sentiment analysis. In Proceedings of the 2022 Conference of the North American… [find](https://scholar.google.com/scholar?q=Fatemehsadat+Mireshghallah%2C+Vaishnavi+Shrivastava%2C+Milad+Shokouhi%2C+Taylor+Berg%2DKirkpatrick%2C+Robert+Sim%2C+and+Dimitrios+Dimitriadis%2E+2022%2E+Useridentifier%3A+Implicit+user+representations+for+simple+and+ef)
18. Saif Mohammad, Felipe Bravo-Marquez, Mohammad Salameh, and Svetlana Kiritchenko. 2018. [Semeval-2018 task 1: Affect in tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2018-semeval-2018-task-1-affect/). In Proceedings of the 12th international workshop on semantic evaluation, pages 1–17.
19. Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, et al. 2024. [Llmlingua-2: Data distillation for efficient and faithful task-agnostic prompt compression](https://md.research.elamur.ai/free/en/papers/pan-2024-llmlingua-2-data-distillation-efficient/). arXiv preprint arXiv:2403.12968.
20. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. [Pytorch: An imperative style, high-performance deep learning library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/). arXiv preprint arXiv:1912.01703.
21. Zhaopeng Qiu, Xian Wu, Jingyue Gao, and Wei Fan. 2021. U-bert: Pre-training user representations for improved recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 4320–4327. [find](https://scholar.google.com/scholar?q=Zhaopeng+Qiu%2C+Xian+Wu%2C+Jingyue+Gao%2C+and+Wei+Fan%2E+2021%2E+U%2Dbert%3A+Pre%2Dtraining+user+representations+for+improved+recommendation%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+3)
22. Nils Karl Reimer, Mohammad Atari, Farzan Karimi-Malekabadi, Jackson Trager, Brendan Kennedy, Jesse Graham, and Morteza Dehghani. 2022. Moral values predict county-level covid-19 vaccination rates in the united states. American Psychologist, 77(6):743. [find](https://scholar.google.com/scholar?q=Nils+Karl+Reimer%2C+Mohammad+Atari%2C+Farzan+Karimi%2DMalekabadi%2C+Jackson+Trager%2C+Brendan+Kennedy%2C+Jesse+Graham%2C+and+Morteza+Dehghani%2E+2022%2E+Moral+values+predict+county%2Dlevel+covid%2D19+vaccination+rates+in+t)
23. Chris Richardson, Yao Zhang, Kellen Gillespie, Sudipta Kar, Arshdeep Singh, Zeynab Raeesy, Omar Zia Khan, and Abhinav Sethy. 2023. Integrating summarization and retrieval for enhanced personalization via large language models. arXiv preprint arXiv:2310.20081. — [arXiv:2310.20081](https://arxiv.org/abs/2310.20081) [find](https://scholar.google.com/scholar?q=Chris+Richardson%2C+Yao+Zhang%2C+Kellen+Gillespie%2C+Sudipta+Kar%2C+Arshdeep+Singh%2C+Zeynab+Raeesy%2C+Omar+Zia+Khan%2C+and+Abhinav+Sethy%2E+2023%2E+Integrating+summarization+and+retrieval+for+enhanced+personalization+)
24. Alireza Salemi, Sheshera Mysore, Michael Bendersky, and Hamed Zamani. 2023. [Lamp: When large language models meet personalization](https://md.research.elamur.ai/free/en/papers/salemi-2024-lamp-when-large-language-models/). arXiv preprint arXiv:2304.11406.
25. Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto. 2023. [Whose opinions do language models reflect?](https://md.research.elamur.ai/free/en/papers/santurkar-2023-whose-opinions-language-models-reflect/) In International Conference on Machine Learning, pages 29971–30004. PMLR.
26. Wenxuan Zhang, Hou Pong Chan, Yiran Zhao, Mahani Aljunied, Jianyu Wang, Chaoqun Liu, Yue Deng, Zhiqiang Hu, Weiwen Xu, Yew Ken Chia, Xin Li, and Lidong Bing. 2024. Seallms 3: Open foundation and chat multilingual large language models for southeast asian languages. CoRR, abs/2407.19672. [find](https://scholar.google.com/scholar?q=Wenxuan+Zhang%2C+Hou+Pong+Chan%2C+Yiran+Zhao%2C+Mahani+Aljunied%2C+Jianyu+Wang%2C+Chaoqun+Liu%2C+Yue+Deng%2C+Zhiqiang+Hu%2C+Weiwen+Xu%2C+Yew+Ken+Chia%2C+Xin+Li%2C+and+Lidong+Bing%2E+2024%2E+Seallms+3%3A+Open+foundation+and+chat+)
27. Krishna Srinivasan, Karthik Raman, Anupam Samanta, Lingrui Liao, Luca Bertelli, and Mike Bendersky. 2022. Quill: Query intent with large language models using retrieval augmentation and multi-stage distillation. arXiv preprint arXiv:2210.15718. [find](https://scholar.google.com/scholar?q=Krishna+Srinivasan%2C+Karthik+Raman%2C+Anupam+Samanta%2C+Lingrui+Liao%2C+Luca+Bertelli%2C+and+Mike+Bendersky%2E+2022%2E+Quill%3A+Query+intent+with+large+language+models+using+retrieval+augmentation+and+multi%2Dstage+di)
28. Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A Smith, Luke Zettlemoyer, and Tao Yu. 2022. [One embedder, any task: Instruction-finetuned text embeddings](https://md.research.elamur.ai/free/en/papers/su-2022-one-embedder-any-task-instruction/). arXiv preprint arXiv:2212.09741.
29. Chenkai Sun, Jinning Li, Hou Pong Chan, ChengXiang Zhai, and Heng Ji. 2023. Measuring the effect of influential messages on varying personas. arXiv preprint arXiv:2305.16470. [find](https://scholar.google.com/scholar?q=Chenkai+Sun%2C+Jinning+Li%2C+Hou+Pong+Chan%2C+ChengXiang+Zhai%2C+and+Heng+Ji%2E+2023%2E+Measuring+the+effect+of+influential+messages+on+varying+personas%2E+arXiv+preprint+arXiv%3A2305%2E16470%2E)
30. Carlos J Torelli and Andrew M Kaikati. 2009. Values as predictors of judgments and behaviors: The role of abstract and concrete mindsets. Journal of personality and social psychology, 96(1):231. [find](https://scholar.google.com/scholar?q=Carlos+J+Torelli+and+Andrew+M+Kaikati%2E+2009%2E+Values+as+predictors+of+judgments+and+behaviors%3A+The+role+of+abstract+and+concrete+mindsets%2E+Journal+of+personality+and+social+psychology%2C+96%281%29%3A231%2E)
31. Hai Wang and David McAllester. 2020. On-the-fly information retrieval augmentation for language models. arXiv preprint arXiv:2007.01528. [find](https://scholar.google.com/scholar?q=Hai+Wang+and+David+McAllester%2E+2020%2E+On%2Dthe%2Dfly+information+retrieval+augmentation+for+language+models%2E+arXiv+preprint+arXiv%3A2007%2E01528%2E)
32. Zhenghui Wang, Lingxiao Luo, and Diyi Yang. 2021. Personalized response generation with tensor factorization. In Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021), pages 47–57. [find](https://scholar.google.com/scholar?q=Zhenghui+Wang%2C+Lingxiao+Luo%2C+and+Diyi+Yang%2E+2021%2E+Personalized+response+generation+with+tensor+factorization%2E+In+Proceedings+of+the+1st+Workshop+on+Natural+Language+Generation%2C+Evaluation%2C+and+Metrics)
33. Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. [Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/). arXiv preprint arXiv:2109.01652.
34. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lho… — [Transformers: State-of-the-Art Natural Language Processing](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)
35. Peitian Zhang, Shitao Xiao, Zheng Liu, Zhicheng Dou, and Jian-Yun Nie. 2023. Retrieve anything to augment large language models. arXiv preprint arXiv:2310.07554. — [arXiv:2310.07554](https://arxiv.org/abs/2310.07554) [find](https://scholar.google.com/scholar?q=Peitian+Zhang%2C+Shitao+Xiao%2C+Zheng+Liu%2C+Zhicheng+Dou%2C+and+Jian%2DYun+Nie%2E+2023%2E+Retrieve+anything+to+augment+large+language+models%2E+arXiv+preprint+arXiv%3A2310%2E07554%2E+%E2%80%94+%5BarXiv%3A2310%2E07554%5D%28https%3A%2F%2Farxiv%2Eorg)

*Updated 31 October 2026*