---
title: "Suri — paper by Pham et al. (2024) — summary and ideas"
description: "The work matters because it offers a way to align long-form generation without costly preference labels. 68 references, cited by 14 papers here."
authors: ["Chau Minh Pham", "Simeng Sun", "Mohit Iyyer"]
year: 2024
venue: "Findings of the Association for Computational Linguistics: EMNLP 2024"
source: "https://aclanthology.org/2024.findings-emnlp.94/"
doi: "10.18653/v1/2024.findings-emnlp.94"
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/pham-2024-suri-multi-constraint-instruction-following/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pham-2024-suri-multi-constraint-instruction-following/)

[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/10/) / Suri: Multi-constraint Instruction Following in Long-form Text Generation

# Suri: Multi-constraint Instruction Following in Long-form Text Generation

**Authors:** [Chau Minh Pham](https://md.research.elamur.ai/free/en/authors/chau-minh-pham/), [Simeng Sun](https://md.research.elamur.ai/free/en/authors/simeng-sun/) and [Mohit Iyyer](https://md.research.elamur.ai/free/en/authors/mohit-iyyer/) · **Year:** 2024 · **Venue:** [Findings of the Association for Computational Linguistics: EMNLP 2024](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2024](https://md.research.elamur.ai/free/en/venues/findings/2024/)) · **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/2024.findings-emnlp.94/) · [PDF](https://aclanthology.org/2024.findings-emnlp.94.pdf) · [DOI 10.18653/v1/2024.findings-emnlp.94](https://doi.org/10.18653/v1/2024.findings-emnlp.94) · [OpenAlex](https://openalex.org/W4404783495)

**Citations:** 5 citations (OpenAlex, 2026-10-14) · [14](https://md.research.elamur.ai/free/en/papers/pham-2024-suri-multi-constraint-instruction-following/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Most instruction-tuning data pairs simple prompts with short answers. This paper addresses a harder setting: requests with many constraints that require outputs thousands of tokens long, such as fiction or detailed non-fiction.

The authors built **Suri**, a 20K-example dataset. They took human-written long texts and had GPT-4-turbo infer a matching instruction for each: a main goal plus about ten stylistic and semantic constraints. Collecting human preferences over such long texts is impractical, so they also had the LLM minimally alter each instruction's constraints until the original text no longer fits them. Their method, **I-ORPO**, adapts ORPO to treat these corrupted instructions as the negative signal, in place of rejected responses.

Both SFT and I-ORPO fine-tuning of Mistral-7B-Instruct-v0.2 raised typical output length from about 1K to about 5K tokens without notable quality loss. Human judges preferred the I-ORPO model for how naturally it worked constraints into the text. The work matters because it offers a way to align long-form generation without costly preference labels.

## Key points
- **Suri data sources:** Texts come in near-equal shares from ChapterBreak (AO3 fanfiction, 6,656), Books3 (6,698) and filtered RedPajama-Data-v2 web documents (6,646).
  - Texts are truncated to 2,048–5,024 words.
  - The data is split 10K/5K/5K into train, validation and test.
  - For Books3, only titles and IDs are released, together with a script to rebuild the samples.
- **Example structure:** Each example contains a backtranslated instruction (x_w), a corrupted instruction (x_l) and a human-written response (y). The authors describe Suri as the first dataset to combine multi-constraint prompts with long responses.
- **Released models:** Suri-SFT and Suri-I-ORPO, both built on Mistral-7B-Instruct-v0.2.
  - Both reach roughly 5K-token generations while keeping n-gram repetition low.
  - Both distinguish correct from corrupted instructions at least 10% better than the base model.
- **LLM judges:** GPT-4o, Gemini-1.5-Pro and Claude-3.5-Sonnet proved unreliable for evaluating long outputs, so the authors relied on human evaluation.
- **Human evaluation:** Suri-I-ORPO beat Suri-SFT in about 67–73% of comparisons on coherence, informativeness and readability. Annotators said the SFT model produced repetition, confusing plots and missing endings.

*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 Massachusetts Amherst](https://md.research.elamur.ai/free/en/universities/university-of-massachusetts-amherst/) — University, Amherst Center, United States · 114 works · 68,731 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [✍️ Text generation](https://md.research.elamur.ai/free/en/topics/text-generation/) · 214 works

## Cite

Cite as: Chau Minh Pham, Simeng Sun and Mohit Iyyer. 2024. Suri: Multi-constraint Instruction Following in Long-form Text Generation. Findings of the Association for Computational Linguistics: EMNLP 2024.

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

```bibtex
@inproceedings{pham2024suri,
  title = {{Suri: Multi-constraint Instruction Following in Long-form Text Generation}},
  author = {Chau Minh Pham, Simeng Sun and Mohit Iyyer},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024},
  year = {2024},
  doi = {10.18653/v1/2024.findings-emnlp.94},
  url = {https://doi.org/10.18653/v1/2024.findings-emnlp.94}
}
```

- [← previous sDPO: Don't Use Your Data All at Once](https://md.research.elamur.ai/free/en/papers/kim-2024-sdpo-don-t-use-data/)
- [next → Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models](https://md.research.elamur.ai/free/en/papers/min-2024-synergetic-event-understanding-collaborative-approach/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/10/)

## References

68 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. AI@Meta. 2024. Llama 3 model card. [find](https://scholar.google.com/scholar?q=AI%40Meta%2E+2024%2E+Llama+3+model+card%2E)
2. Anthropic. 2024. Introducing Claude 3.5 Sonnet. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2024%2E+Introducing+Claude+3%2E5+Sonnet%2E)
3. Amanda Askell, Yuntao Bai, Anna Chen, Dawn Drain, Deep Ganguli, Tom Henighan, Andy Jones, Nicholas Joseph, Ben Mann, Nova DasSarma, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Jackson Kernion, Kamal Ndousse, Catherine Olsson, Dario Amodei, Tom Brown, Jack Clark, Sam McCandlish, Chris Olah, a… [find](https://scholar.google.com/scholar?q=Amanda+Askell%2C+Yuntao+Bai%2C+Anna+Chen%2C+Dawn+Drain%2C+Deep+Ganguli%2C+Tom+Henighan%2C+Andy+Jones%2C+Nicholas+Joseph%2C+Ben+Mann%2C+Nova+DasSarma%2C+Nelson+Elhage%2C+Zac+Hatfield%2DDodds%2C+Danny+Hernandez%2C+Jackson+Kernion%2C)
4. Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, Carol Chen, Catherine Olsson, Christopher Olah, Danny Hernandez, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jamie Kerr, Jared… — [Constitutional AI: Harmlessness from AI Feedback](https://md.research.elamur.ai/free/en/papers/bai-2022-constitutional-ai-harmlessness-ai-feedback/)
5. Yushi Bai, Xin Lv, Jiajie Zhang, Yuze He, Ji Qi, Lei Hou, Jie Tang, Yuxiao Dong, and Juanzi Li. 2024. [LongAlign: A Recipe for Long Context Alignment of Large Language Models](https://md.research.elamur.ai/free/en/papers/bai-2024-longalign-recipe-long-context/)! arXiv preprint. ArXiv:2401.18058 [cs].
6. BernhardClemm. 2023. v2.0.0 (v2.0.0). ercexpo/us-news-domains: Dallas Card, Peter Henderson, Urvashi Khandelwal, Robin Jia, Kyle Mahowald, and Dan Jurafsky. 2020. With little power comes great responsibility. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (… [find](https://scholar.google.com/scholar?q=BernhardClemm%2E+2023%2E+v2%2E0%2E0+%28v2%2E0%2E0%29%2E+ercexpo%2Fus%2Dnews%2Ddomains%3A+Dallas+Card%2C+Peter+Henderson%2C+Urvashi+Khandelwal%2C+Robin+Jia%2C+Kyle+Mahowald%2C+and+Dan+Jurafsky%2E+2020%2E+With+little+power+comes+great+respons)
7. Angelica Chen, Sadhika Malladi, Lily H. Zhang, Xinyi Chen, Qiuyi Zhang, Rajesh Ranganath, and Kyunghyun Cho. 2024a. Preference learning algorithms do not learn preference rankings. Preprint, arXiv:2405.19534. [find](https://scholar.google.com/scholar?q=Angelica+Chen%2C+Sadhika+Malladi%2C+Lily+H%2E+Zhang%2C+Xinyi+Chen%2C+Qiuyi+Zhang%2C+Rajesh+Ranganath%2C+and+Kyunghyun+Cho%2E+2024a%2E+Preference+learning+algorithms+do+not+learn+preference+rankings%2E+Preprint%2C+arXiv%3A240)
8. Yukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han, and Jiaya Jia. 2024b. [Longlora: Efficient fine-tuning of long-context large language models](https://md.research.elamur.ai/free/en/papers/chen-2023-longlora-efficient-fine-tuning-long/). Preprint, arXiv:2309.12307.
9. Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Yunxuan Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Alex Castro-Ros, Marie Pellat, Kevin Robinson, Dasha Valter, Sharan… [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+Albert+Webson%2C+Shixiang+Shane+Gu%2C+Zhuyun+Dai%2C+Mirac+Suzgun%2C+X)
10. Together Computer. 2023. [Redpajama: an open dataset for training large language models](https://md.research.elamur.ai/free/en/papers/weber-2024-redpajama-open-dataset-training-large/).
11. Mike Conover, Matt Hayes, Ankit Mathur, Jianwei Xie, Jun Wan, Sam Shah, Ali Ghodsi, Patrick Wendell, Matei Zaharia, and Reynold Xin. 2023. Free dolly: Introducing the world’s first truly open instruction-tuned llm. [find](https://scholar.google.com/scholar?q=Mike+Conover%2C+Matt+Hayes%2C+Ankit+Mathur%2C+Jianwei+Xie%2C+Jun+Wan%2C+Sam+Shah%2C+Ali+Ghodsi%2C+Patrick+Wendell%2C+Matei+Zaharia%2C+and+Reynold+Xin%2E+2023%2E+Free+dolly%3A+Introducing+the+world%E2%80%99s+first+truly+open+instruct)
12. Tri Dao. 2024. [FlashAttention-2: Faster attention with better parallelism and work partitioning](https://md.research.elamur.ai/free/en/papers/dao-2023-flashattention-2-faster-attention-better/). In International Conference on Learning Representations (ICLR).
13. Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, and Douwe Kiela. 2024. Kto: Model alignment as prospect theoretic optimization. Preprint, arXiv:2402.01306. [find](https://scholar.google.com/scholar?q=Kawin+Ethayarajh%2C+Winnie+Xu%2C+Niklas+Muennighoff%2C+Dan+Jurafsky%2C+and+Douwe+Kiela%2E+2024%2E+Kto%3A+Model+alignment+as+prospect+theoretic+optimization%2E+Preprint%2C+arXiv%3A2402%2E01306%2E)
14. Angela Fan, Mike Lewis, and Yann Dauphin. 2018. [Hierarchical neural story generation](https://md.research.elamur.ai/free/en/papers/fan-2018-hierarchical-neural-story-generation/). Preprint, arXiv:1805.04833.
15. Leo Gao, Stella Biderman, Sid Black, Laurence Golding, Travis Hoppe, Charles Foster, Jason Phang, Horace He, Anish Thite, Noa Nabeshima, Shawn Presser, and Connor Leahy. 2020. The Pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027. [find](https://scholar.google.com/scholar?q=Leo+Gao%2C+Stella+Biderman%2C+Sid+Black%2C+Laurence+Golding%2C+Travis+Hoppe%2C+Charles+Foster%2C+Jason+Phang%2C+Horace+He%2C+Anish+Thite%2C+Noa+Nabeshima%2C+Shawn+Presser%2C+and+Connor+Leahy%2E+2020%2E+The+Pile%3A+An+800gb+datas)
16. Leo Gao, Jonathan Tow, Baber Abbasi, Stella Biderman, Sid Black, Anthony DiPofi, Charles Foster, Laurence Golding, Jeffrey Hsu, Alain Le Noac’h, Haonan Li, Kyle McDonell, Niklas Muennighoff, Chris Ociepa, Jason Phang, Laria Reynolds, Hailey Schoelkopf, Aviya Skowron, Lintang Sutawika, Eric Tang, Ani… [find](https://scholar.google.com/scholar?q=Leo+Gao%2C+Jonathan+Tow%2C+Baber+Abbasi%2C+Stella+Biderman%2C+Sid+Black%2C+Anthony+DiPofi%2C+Charles+Foster%2C+Laurence+Golding%2C+Jeffrey+Hsu%2C+Alain+Le+Noac%E2%80%99h%2C+Haonan+Li%2C+Kyle+McDonell%2C+Niklas+Muennighoff%2C+Chris+Oci)
17. Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, and Minlie Huang. 2021. Long text generation by modeling sentence-level and discourse-level coherence. Preprint, arXiv:2105.08963. [find](https://scholar.google.com/scholar?q=Jian+Guan%2C+Xiaoxi+Mao%2C+Changjie+Fan%2C+Zitao+Liu%2C+Wenbiao+Ding%2C+and+Minlie+Huang%2E+2021%2E+Long+text+generation+by+modeling+sentence%2Dlevel+and+discourse%2Dlevel+coherence%2E+Preprint%2C+arXiv%3A2105%2E08963%2E)
18. Jiwoo Hong, Noah Lee, and James Thorne. 2024. Orpo: Monolithic preference optimization without reference model. Preprint, arXiv:2403.07691. [find](https://scholar.google.com/scholar?q=Jiwoo+Hong%2C+Noah+Lee%2C+and+James+Thorne%2E+2024%2E+Orpo%3A+Monolithic+preference+optimization+without+reference+model%2E+Preprint%2C+arXiv%3A2403%2E07691%2E)
19. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). Preprint, arXiv:2106.09685.
20. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… [find](https://scholar.google.com/scholar?q=Albert+Q%2E+Jiang%2C+Alexandre+Sablayrolles%2C+Arthur+Mensch%2C+Chris+Bamford%2C+Devendra+Singh+Chaplot%2C+Diego+de+las+Casas%2C+Florian+Bressand%2C+Gianna+Lengyel%2C+Guillaume+Lample%2C+Lucile+Saulnier%2C+L%C3%A9lio+Renard+Lav)
21. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. [A diversity-promoting objective function for neural conversation models](https://md.research.elamur.ai/free/en/papers/li-2016-diversity-promoting-objective-function-neural/). In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pag…
22. 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, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock,… [find](https://scholar.google.com/scholar?q=Albert+Q%2E+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+Gianna+Lengyel%2C+Guill)
23. Xian Li, Ping Yu, Chunting Zhou, Timo Schick, Luke Zettlemoyer, Omer Levy, Jason Weston, and Mike Lewis. 2023. [Self-alignment with instruction back-translation](https://md.research.elamur.ai/free/en/papers/li-2023-self-alignment-instruction-backtranslation/). arXiv preprint arXiv:2308.06259.
24. Yekyung Kim, Yapei Chang, Marzena Karpinska, Aparna Garimella, Varun Manjunatha, Kyle Lo, Tanya Goyal, and Mohit Iyyer. 2024. Fables: Evaluating faithfulness and content selection in book-length summarization. Preprint, arXiv:2404.01261. — [arXiv:2404.01261](https://arxiv.org/abs/2404.01261) [find](https://scholar.google.com/scholar?q=Yekyung+Kim%2C+Yapei+Chang%2C+Marzena+Karpinska%2C+Aparna+Garimella%2C+Varun+Manjunatha%2C+Kyle+Lo%2C+Tanya+Goyal%2C+and+Mohit+Iyyer%2E+2024%2E+Fables%3A+Evaluating+faithfulness+and+content+selection+in+book%2Dlength+summa)
25. Julia Kreutzer, Joshua Uyheng, and Stefan Riezler. 2018. [Reliability and learnability of human bandit feedback for sequence-to-sequence reinforcement learning](https://md.research.elamur.ai/free/en/papers/kreutzer-2018-reliability-learnability-human-bandit-feedback/). In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1777–1788, Melbour…
26. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
27. Abdullatif Köksal, Timo Schick, Anna Korhonen, and Hinrich Schütze. 2023. LongForm: Optimizing Instruction Tuning for Long Text Generation with Corpus Extraction. arXiv preprint. ArXiv:2304.08460 [cs]. — [arXiv:2304.08460](https://arxiv.org/abs/2304.08460) [find](https://scholar.google.com/scholar?q=Abdullatif+K%C3%B6ksal%2C+Timo+Schick%2C+Anna+Korhonen%2C+and+Hinrich+Sch%C3%BCtze%2E+2023%2E+LongForm%3A+Optimizing+Instruction+Tuning+for+Long+Text+Generation+with+Corpus+Extraction%2E+arXiv+preprint%2E+ArXiv%3A2304%2E08460+%5Bcs%5D)
28. Hao Liu, Carmelo Sferrazza, and Pieter Abbeel. 2023. [Chain of hindsight aligns language models with feedback](https://md.research.elamur.ai/free/en/papers/liu-2023-chain-hindsight-aligns-language-models/). Preprint, arXiv:2302.02676.
29. Chaitanya Malaviya, Priyanka Agrawal, Kuzman Ganchev, Pranesh Srinivasan, Fantine Huot, Jonathan Berant, Mark Yatskar, Dipanjan Das, Mirella Lapata, and Chris Alberti. 2024. [Dolomites: Domain-specific long-form methodical tasks](https://md.research.elamur.ai/free/en/papers/malaviya-2025-dolomites-domain-specific-long-form/). In arXiv.
30. Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, Sayak Paul, and Benjamin Bossan. 2022. Peft: State-of-the-art parameter-efficient fine-tuning methods. [https://github.com/huggingface/peft](https://github.com/huggingface/peft). [↗](https://github.com/huggingface/peft)
31. Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2022. Cross-task generalization via natural language crowdsourcing instructions. Preprint, arXiv:2104.08773. [find](https://scholar.google.com/scholar?q=Swaroop+Mishra%2C+Daniel+Khashabi%2C+Chitta+Baral%2C+and+Hannaneh+Hajishirzi%2E+2022%2E+Cross%2Dtask+generalization+via+natural+language+crowdsourcing+instructions%2E+Preprint%2C+arXiv%3A2104%2E08773%2E)
32. Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He, Devi Parikh, Dhruv Batra, Lucy Vanderwende, Pushmeet Kohli, and James Allen. 2016. A corpus and cloze evaluation for deeper understanding of commonsense stories. In Proceedings of the 2016 Conference of the North American Chapter of the Associati… [find](https://scholar.google.com/scholar?q=Nasrin+Mostafazadeh%2C+Nathanael+Chambers%2C+Xiaodong+He%2C+Devi+Parikh%2C+Dhruv+Batra%2C+Lucy+Vanderwende%2C+Pushmeet+Kohli%2C+and+James+Allen%2E+2016%2E+A+corpus+and+cloze+evaluation+for+deeper+understanding+of+commo)
33. OpenAI. 2024. Model release blog: GPT-4o. Technical report, OpenAI. Accessed: 2024-05-23. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Model+release+blog%3A+GPT%2D4o%2E+Technical+report%2C+OpenAI%2E+Accessed%3A+2024%2D05%2D23%2E)
34. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. [Train…](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
35. Andreas Köpf, Yannic Kilcher, Dimitri von Rütte, Sotiris Anagnostidis, Zhi-Rui Tam, Keith Stevens, Abdullah Barhoum, Nguyen Minh Duc, Oliver Stanley, Richárd Nagyfi, Shahul ES, Sameer Suri, David Glushkov, Arnav Dantuluri, Andrew Maguire, Christoph Schuhmann, Huu Nguyen, and Alexander Mattick. 2023.… — [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://md.research.elamur.ai/free/en/papers/kopf-2023-openassistant-conversations-democratizing-large-language/)
36. Shawn Presser. 2020. Books3. [find](https://scholar.google.com/scholar?q=Shawn+Presser%2E+2020%2E+Books3%2E)
37. Harrison Lee, Samrat Phatale, Hassan Mansoor, Kellie Lu, Thomas Mesnard, Colton Bishop, Victor Carbune, and Abhinav Rastogi. 2023. Rlaif: Scaling reinforcement learning from human feedback with ai feedback. arXiv preprint arXiv:2309.00267. [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+2023%2E+Rlaif%3A+Scaling+reinforcement+learning+from+human+feedback+with+ai+fee)
38. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D. Manning, and Chelsea Finn. 2023. [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/). Preprint, arXiv:2305.18290.
39. Nazneen Rajani, Lewis Tunstall, Edward Beeching, Nathan Lambert, Alexander M. Rush, and Thomas Wolf. 2023. No robots. [https://huggingface.co/](https://huggingface.co/) datasets/HuggingFaceH4/no_robots. [↗](https://huggingface.co/)
40. Rajkumar Ramamurthy, Prithviraj Ammanabrolu, Kianté Brantley, Jack Hessel, Rafet Sifa, Christian Bauckhage, Hannaneh Hajishirzi, and Yejin Choi. 2023. [Is reinforcement learning (not) for natural language processing: Benchmarks, baselines, and building blocks for natural language policy optimization](https://md.research.elamur.ai/free/en/papers/ramamurthy-2022-reinforcement-learning-natural-language-processing/).…
41. Jeff Rasley, Samyam Rajbhandari, Olatunji Ruwase, and Yuxiong He. 2020. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’20, page 3505–3506,… [find](https://scholar.google.com/scholar?q=Jeff+Rasley%2C+Samyam+Rajbhandari%2C+Olatunji+Ruwase%2C+and+Yuxiong+He%2E+2020%2E+Deepspeed%3A+System+optimizations+enable+training+deep+learning+models+with+over+100+billion+parameters%2E+In+Proceedings+of+the+26t)
42. Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, Manan Dey, M Saiful Bari, Canwen Xu, Urmish Thakker, Shanya Sharma Sharma, Eliza Szczechla, Taewoon Kim, Gunjan Chhablani, Nihal Nayak, Debajyoti Da… — [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://md.research.elamur.ai/free/en/papers/sanh-2021-multitask-prompted-training-enables-zero/)
43. Abigail See, Aneesh Pappu, Rohun Saxena, Akhila Yerukola, and Christopher D. Manning. 2019. [Do massively pretrained language models make better storytellers?](https://md.research.elamur.ai/free/en/papers/see-2019-massively-pretrained-language-models-make/) Preprint, arXiv:1909.10705.
44. Uri Shaham, Elad Segal, Maor Ivgi, Avia Efrat, Ori Yoran, Adi Haviv, Ankit Gupta, Wenhan Xiong, Mor Geva, Jonathan Berant, and Omer Levy. 2022. [Scrolls: Standardized comparison over long language sequences](https://md.research.elamur.ai/free/en/papers/shaham-2022-scrolls-standardized-comparison-over-long/). Preprint, arXiv:2201.03533.
45. Nisan Stiennon, Long Ouyang, Jeff Wu, Daniel M. Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul Christiano. 2022. Learning to summarize from human feedback. Preprint, arXiv:2009.01325. [find](https://scholar.google.com/scholar?q=Nisan+Stiennon%2C+Long+Ouyang%2C+Jeff+Wu%2C+Daniel+M%2E+Ziegler%2C+Ryan+Lowe%2C+Chelsea+Voss%2C+Alec+Radford%2C+Dario+Amodei%2C+and+Paul+Christiano%2E+2022%2E+Learning+to+summarize+from+human+feedback%2E+Preprint%2C+arXiv%3A2009)
46. Simeng Sun, Katherine Thai, and Mohit Iyyer. 2022. Chapterbreak: A challenge dataset for long-range language models. arXiv preprint arXiv:2204.10878. [find](https://scholar.google.com/scholar?q=Simeng+Sun%2C+Katherine+Thai%2C+and+Mohit+Iyyer%2E+2022%2E+Chapterbreak%3A+A+challenge+dataset+for+long%2Drange+language+models%2E+arXiv+preprint+arXiv%3A2204%2E10878%2E)
47. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford alpaca: An instruction-following llama model. [https://github.com/tatsu-lab/stanford_alpaca](https://github.com/tatsu-lab/stanford_alpaca). [↗](https://github.com/tatsu-lab/stanford_alpaca)
48. Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, Soroosh Mariooryad, Yifan Ding, Xinyang Geng, Fred Alcober, Roy Frostig, Mark Omernick, Lexi Walker, Cosmin Paduraru, Christina Sorokin, Andrea Tacchetti, Colin… — [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://md.research.elamur.ai/free/en/papers/gemini-team-2024-gemini-1-5-unlocking-multimodal/)
49. The Association of Religion Data Archives. 2023. Religion dictionary. [https://www.thearda.com/research/religion-dictionary](https://www.thearda.com/research/religion-dictionary). Accessed: 2024/01/15. [↗](https://www.thearda.com/research/religion-dictionary)
50. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
51. Lewis Tunstall, Edward Beeching, Nathan Lambert, Nazneen Rajani, Shengyi Huang, Kashif Rasul, Alexander M. Rush, and Thomas Wolf. 2023. The alignment handbook. [https://github.com/](https://github.com/) huggingface/alignment-handbook. [↗](https://github.com/)
52. David Wadden, Kelsey MacMillan, Noah A. Smith, Iz Beltagy, and Hannaneh Hajishirzi. 2023b. [How far can camels go? exploring the state of instruction tuning on open resources](https://md.research.elamur.ai/free/en/papers/wang-2023-far-camels-go-exploring-state/). Preprint, arXiv:2306.04751.
53. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2023c. Self-instruct: Aligning language models with self-generated instructions. Preprint, arXiv:2212.10560. [find](https://scholar.google.com/scholar?q=Yizhong+Wang%2C+Yeganeh+Kordi%2C+Swaroop+Mishra%2C+Alisa+Liu%2C+Noah+A%2E+Smith%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+2023c%2E+Self%2Dinstruct%3A+Aligning+language+models+with+self%2Dgenerated+instructions%2E+Prepri)
54. Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, Eshaan Pathak, Giannis Karamanolakis, Haizhi Gary Lai, Ishan Purohit, Ishani Mondal, Jacob Anderson, Kirby Kuznia, Krima Doshi, Ma… [find](https://scholar.google.com/scholar?q=Yizhong+Wang%2C+Swaroop+Mishra%2C+Pegah+Alipoormolabashi%2C+Yeganeh+Kordi%2C+Amirreza+Mirzaei%2C+Anjana+Arunkumar%2C+Arjun+Ashok%2C+Arut+Selvan+Dhanasekaran%2C+Atharva+Naik%2C+David+Stap%2C+Eshaan+Pathak%2C+Giannis+Karaman)
55. 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.
56. Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. 2022. [Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/). Preprint, arXiv:2109.01652.
57. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Rémi 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/)
58. Rose E Wang, Esin Durmus, Noah Goodman, and Tatsunori Hashimoto. 2023a. Language modeling via stochastic processes. Preprint, arXiv:2203.11370. — [arXiv:2203.11370](https://arxiv.org/abs/2203.11370) [find](https://scholar.google.com/scholar?q=Rose+E+Wang%2C+Esin+Durmus%2C+Noah+Goodman%2C+and+Tatsunori+Hashimoto%2E+2023a%2E+Language+modeling+via+stochastic+processes%2E+Preprint%2C+arXiv%3A2203%2E11370%2E+%E2%80%94+%5BarXiv%3A2203%2E11370%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2203%2E11370%29)
59. Wenhan Xiong, Jingyu Liu, Igor Molybog, Hejia Zhang, Prajjwal Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang, and Hao Ma.… — [Effective Long-Context Scaling of Foundation Models](https://md.research.elamur.ai/free/en/papers/xiong-2023-effective-long-context-scaling-foundation/)
60. Yizhong Wang, Hamish Ivison, Pradeep Dasigi, Jack Hessel, Tushar Khot, Khyathi Raghavi Chandu, Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, and Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, and Shengyi Huang.… [find](https://scholar.google.com/scholar?q=Yizhong+Wang%2C+Hamish+Ivison%2C+Pradeep+Dasigi%2C+Jack+Hessel%2C+Tushar+Khot%2C+Khyathi+Raghavi+Chandu%2C+Can+Xu%2C+Qingfeng+Sun%2C+Kai+Zheng%2C+Xiubo+Geng%2C+Pu+Zhao%2C+Jiazhan+Feng%2C+Chongyang+Tao%2C+and+Leandro+von+Werra%2C)
61. Daxin Jiang. 2023a. [Wizardlm: Empowering large language models to follow complex instructions](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/). Preprint, arXiv:2304.12244.
62. Canwen Xu, Daya Guo, Nan Duan, and Julian McAuley. 2023b. [Baize: An open-source chat model with parameter-efficient tuning on self-chat data](https://md.research.elamur.ai/free/en/papers/xu-2023-baize-open-source-chat-model/). arXiv preprint arXiv:2304.01196.
63. Fangyuan Xu, Kyle Lo, Luca Soldaini, Bailey Kuehl, Eunsol Choi, and David Wadden. 2024. KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions. arXiv preprint. ArXiv:2403.03866 [cs]. [find](https://scholar.google.com/scholar?q=Fangyuan+Xu%2C+Kyle+Lo%2C+Luca+Soldaini%2C+Bailey+Kuehl%2C+Eunsol+Choi%2C+and+David+Wadden%2E+2024%2E+KIWI%3A+A+Dataset+of+Knowledge%2DIntensive+Writing+Instructions+for+Answering+Research+Questions%2E+arXiv+preprint%2E+Ar)
64. Fangyuan Xu, Yixiao Song, Mohit Iyyer, and Eunsol Choi. 2023c. [A critical evaluation of evaluations for long-form question answering](https://md.research.elamur.ai/free/en/papers/xu-2023-critical-evaluation-evaluations-long-form/). Preprint, arXiv:2305.18201.
65. Da Yin, Xiao Liu, Fan Yin, Ming Zhong, Hritik Bansal, Jiawei Han, and Kai-Wei Chang. 2023. Dynosaur: A dynamic growth paradigm for instruction-tuning data curation. arXiv preprint arXiv:2305.14327. [find](https://scholar.google.com/scholar?q=Da+Yin%2C+Xiao+Liu%2C+Fan+Yin%2C+Ming+Zhong%2C+Hritik+Bansal%2C+Jiawei+Han%2C+and+Kai%2DWei+Chang%2E+2023%2E+Dynosaur%3A+A+dynamic+growth+paradigm+for+instruction%2Dtuning+data+curation%2E+arXiv+preprint+arXiv%3A2305%2E14327%2E)
66. Chunting Zhou, Pengfei Liu, Puxin Xu, Srinivasan Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, et al. 2024. Lima: Less is more for alignment. Advances in Neural Information Processing Systems, 36. [find](https://scholar.google.com/scholar?q=Chunting+Zhou%2C+Pengfei+Liu%2C+Puxin+Xu%2C+Srinivasan+Iyer%2C+Jiao+Sun%2C+Yuning+Mao%2C+Xuezhe+Ma%2C+Avia+Efrat%2C+Ping+Yu%2C+Lili+Yu%2C+et+al%2E+2024%2E+Lima%3A+Less+is+more+for+alignment%2E+Advances+in+Neural+Information+Proc)
67. Wangchunshu Zhou, Yuchen Eleanor Jiang, Ethan Wilcox, Ryan Cotterell, and Mrinmaya Sachan. 2023. Controlled text generation with natural language instructions. Preprint, arXiv:2304.14293. — [arXiv:2304.14293](https://arxiv.org/abs/2304.14293) [find](https://scholar.google.com/scholar?q=Wangchunshu+Zhou%2C+Yuchen+Eleanor+Jiang%2C+Ethan+Wilcox%2C+Ryan+Cotterell%2C+and+Mrinmaya+Sachan%2E+2023%2E+Controlled+text+generation+with+natural+language+instructions%2E+Preprint%2C+arXiv%3A2304%2E14293%2E+%E2%80%94+%5BarXiv%3A230)
68. Daniel M. Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B. Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 2020. Fine-tuning language models from human preferences. Preprint, arXiv:1909.08593. [find](https://scholar.google.com/scholar?q=Daniel+M%2E+Ziegler%2C+Nisan+Stiennon%2C+Jeffrey+Wu%2C+Tom+B%2E+Brown%2C+Alec+Radford%2C+Dario+Amodei%2C+Paul+Christiano%2C+and+Geoffrey+Irving%2E+2020%2E+Fine%2Dtuning+language+models+from+human+preferences%2E+Preprint%2C+arXiv)

*Updated 2 November 2026*