---
title: "We Are What We Repeatedly Do: Improving Long Context"
description: "On this basis they build VerIFY, a benchmark in which one instruction is given at the start and must hold across a conversation… 49 references."
authors: ["Preston K Robinette", "Andrew Hard", "Swaroop Ramaswamy", "Ehsan Amid", "Rajiv Mathews", "Taylor T Johnson"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.254/"
doi: "10.18653/v1/2026.findings-eacl.254"
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/robinette-2026-we-are-what-we-repeatedly/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/robinette-2026-we-are-what-we-repeatedly/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/47/) / We Are What We Repeatedly Do: Improving Long Context Instruction Following

# We Are What We Repeatedly Do: Improving Long Context Instruction Following

**Authors:** Preston K Robinette, Andrew Hard, Swaroop Ramaswamy, Ehsan Amid, [Rajiv Mathews](https://md.research.elamur.ai/free/en/authors/rajiv-mathews/) and Taylor T Johnson · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **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/2026.findings-eacl.254/) · [PDF](https://aclanthology.org/2026.findings-eacl.254.pdf) · [DOI 10.18653/v1/2026.findings-eacl.254](https://doi.org/10.18653/v1/2026.findings-eacl.254) · [OpenAlex](https://openalex.org/W7140097972)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
LLM context windows have grown enormously, but models tend to drift away from user instructions as conversations get longer. Existing instruction-following benchmarks mostly test single prompts or a few turns, and LongIns covers long inputs but only in a single turn. The authors formalize "verifiable instructions," meaning instructions whose satisfaction a verifier can decide as True/False. They measure adherence with Certified Compliance Accuracy (CCA). On this basis they build VerIFY, a benchmark in which one instruction is given at the start and must hold across a conversation of up to 50 turns. The conversation is padded with filler from QA or dialogue corpora, and the filler's earlier assistant replies either comply, violate, or are left untouched. Experiments with Gemma and Llama models show a clear pattern: models imitate the behaviour already present in the conversation history. The authors then test six mitigation strategies, five prompt-based and one model-based (IGA), and report CCA gains of up to 79%. This is presented as the first study of instruction following in long, multi-turn dialogue.

## Key points
- **VerIFY design:** 28 unique instructions built from 10 formats, grouped into three categories: Style, Security and Alignment. Conversations range from 1 to 50 turns.
- **Filler data:** padding comes from the I'm Feeling Curious QA dataset (HuggingFace) or DailyDialog. Three filler patterns are used: base, rogue and follows.
- **Models tested:** Gemma 7b-it, Gemma2-27b-it, Llama3 8b and Llama3 70b. All evaluations use user prompts only, with no system prompts.
- **Mitigation strategies:** the prompt-based ones are reinstruct, teach, rewrite, combine and summarize, alongside the model-based IGA. They were tested with an "inject 5 away" protocol, where a non-compliant reply is planted 5 turns before evaluation, on 10-, 25- and 50-turn QA conversations.
- **Results:**
  - For Gemma2 27B-it, every strategy beat the baseline, and IGA was best, with gains of up to 79%.
  - For Gemma 7B-it, Combine and IGA failed. Combine suffered from repeated exposure to protected words, and IGA from punts.
  - Code and data are available at github.com/pkrobinette/VerIFY.

*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

- [Vanderbilt University](https://md.research.elamur.ai/free/en/universities/vanderbilt-university/) — University, Nashville, United States · 14 works · 1,413 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

## Cite

Cite as: Preston K Robinette, Andrew Hard, Swaroop Ramaswamy, Ehsan Amid, Rajiv Mathews and Taylor T Johnson. 2026. We Are What We Repeatedly Do: Improving Long Context Instruction Following. Findings of the Association for Computational Linguistics: EACL 2026.

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

```bibtex
@inproceedings{robinette2026we,
  title = {{We Are What We Repeatedly Do: Improving Long Context Instruction Following}},
  author = {Preston K Robinette, Andrew Hard, Swaroop Ramaswamy, Ehsan Amid, Rajiv Mathews and Taylor T Johnson},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.254},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.254}
}
```

- [← previous WaveDetect: Robust Framework for Machine-Generated Text Detection via Wavelet Transform](https://md.research.elamur.ai/free/en/papers/liu-2026-wavedetect-robust-framework-machine-generated/)
- [next → Weakly-supervised Argument Mining with Boundary Refinement and Relation Denoising](https://md.research.elamur.ai/free/en/papers/sun-2026-weakly-supervised-argument-mining-boundary/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/47/)

## References

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

1. Rishabh Agarwal, Avi Singh, Lei M Zhang, Bernd Bohnet, Stephanie Chan, Ankesh Anand, Zaheer Abbas, Azade Nova, John D Co-Reyes, Eric Chu, et al. 2024. [Many-shot in-context learning](https://md.research.elamur.ai/free/en/papers/agarwal-2024-many-shot-context-learning/). arXiv preprint arXiv:2404.11018.
2. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al. 2022a. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862. [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+2022a%2E+Training+a+helpful+and+harmless+assistant+with+rei)
3. Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen, Anna Goldie, Azalia Mirhoseini, Cameron McKinnon, et al. 2022b. [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.
4. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 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.
5. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. [Evaluating large language models trained on code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/). arXiv preprint arXiv:2107.03374.
6. Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30. [find](https://scholar.google.com/scholar?q=Paul+F+Christiano%2C+Jan+Leike%2C+Tom+Brown%2C+Miljan+Martic%2C+Shane+Legg%2C+and+Dario+Amodei%2E+2017%2E+Deep+reinforcement+learning+from+human+preferences%2E+Advances+in+neural+information+processing+systems%2C+30%2E)
7. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/), 2021. URL https://arxiv.org/abs/2110.14168. [↗](https://arxiv.org/abs/2110.14168)
8. Yann Dubois, Chen Xuechen Li, Rohan Taori, Tianyi Zhang, Ishaan Gulrajani, Jimmy Ba, Carlos Guestrin, Percy S Liang, and Tatsunori B Hashimoto. 2024. [Alpacafarm: A simulation framework for methods that learn from human feedback](https://md.research.elamur.ai/free/en/papers/dubois-2023-alpacafarm-simulation-framework-methods-that/). Advances in Neural Information Processing Systems, 36.
9. Shawn Gavin, Tuney Zheng, Jiaheng Liu, Quehry Que, Noah Wang, Jian Yang, Chenchen Zhang, Wenhao Huang, Wenhu Chen, and Ge Zhang. 2024. Longins: A challenging long-context instruction-based exam for llms. arXiv preprint arXiv:2406.17588. — [arXiv:2406.17588](https://arxiv.org/abs/2406.17588) [find](https://scholar.google.com/scholar?q=Shawn+Gavin%2C+Tuney+Zheng%2C+Jiaheng+Liu%2C+Quehry+Que%2C+Noah+Wang%2C+Jian+Yang%2C+Chenchen+Zhang%2C+Wenhao+Huang%2C+Wenhu+Chen%2C+and+Ge+Zhang%2E+2024%2E+Longins%3A+A+challenging+long%2Dcontext+instruction%2Dbased+exam+for+ll)
10. Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, and Jonathan Berant. 2021. Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies. Transactions of the Association for Computational Linguistics, 9:346–361. [find](https://scholar.google.com/scholar?q=Mor+Geva%2C+Daniel+Khashabi%2C+Elad+Segal%2C+Tushar+Khot%2C+Dan+Roth%2C+and+Jonathan+Berant%2E+2021%2E+Did+aristotle+use+a+laptop%3F+a+question+answering+benchmark+with+implicit+reasoning+strategies%2E+Transactions+of+)
11. Qianyu He, Jie Zeng, Wenhao Huang, Lina Chen, Jin Xiao, Qianxi He, Xunzhe Zhou, Jiaqing Liang, and Yanghua Xiao. 2024a. Can large language models understand real-world complex instructions? In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18188–18196. [find](https://scholar.google.com/scholar?q=Qianyu+He%2C+Jie+Zeng%2C+Wenhao+Huang%2C+Lina+Chen%2C+Jin+Xiao%2C+Qianxi+He%2C+Xunzhe+Zhou%2C+Jiaqing+Liang%2C+and+Yanghua+Xiao%2E+2024a%2E+Can+large+language+models+understand+real%2Dworld+complex+instructions%3F+In+Proceed)
12. Yun He, Di Jin, Chaoqi Wang, Chloe Bi, Karishma Mandyam, Hejia Zhang, Chen Zhu, Ning Li, Tengyu Xu, Hongjiang Lv, Shruti Bhosale, Chenguang Zhu, Karthik Abinav Sankararaman, Eryk Helenowski, Melanie Kambadur, Aditya Tayade, Hao Ma, Han Fang, and Sinong Wang. 2024b. Multi-if: Benchmarking llms on mul… — [arXiv:2410.15553](https://arxiv.org/abs/2410.15553) [find](https://scholar.google.com/scholar?q=Yun+He%2C+Di+Jin%2C+Chaoqi+Wang%2C+Chloe+Bi%2C+Karishma+Mandyam%2C+Hejia+Zhang%2C+Chen+Zhu%2C+Ning+Li%2C+Tengyu+Xu%2C+Hongjiang+Lv%2C+Shruti+Bhosale%2C+Chenguang+Zhu%2C+Karthik+Abinav+Sankararaman%2C+Eryk+Helenowski%2C+Melanie+K)
13. Or Honovich, Thomas Scialom, Omer Levy, and Timo Schick. 2022. [Unnatural instructions: Tuning language models with (almost) no human labor](https://md.research.elamur.ai/free/en/papers/honovich-2023-unnatural-instructions-tuning-language-models/). arXiv preprint arXiv:2212.09689.
14. Pingchuan Ma, Rui Ding, Shuai Wang, Shi Han, and Dongmei Zhang. 2023. Insightpilot: An llm-empowered automated data exploration system. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 346–352. [find](https://scholar.google.com/scholar?q=Pingchuan+Ma%2C+Rui+Ding%2C+Shuai+Wang%2C+Shi+Han%2C+and+Dongmei+Zhang%2E+2023%2E+Insightpilot%3A+An+llm%2Dempowered+automated+data+exploration+system%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Na)
15. Yannick Metz, David Lindner, Raphaël Baur, Daniel Keim, and Mennatallah El-Assady. 2023. Rlhf-blender: A configurable interactive interface for learning from diverse human feedback. arXiv preprint arXiv:2308.04332. — [arXiv:2308.04332](https://arxiv.org/abs/2308.04332) [find](https://scholar.google.com/scholar?q=Yannick+Metz%2C+David+Lindner%2C+Rapha%C3%ABl+Baur%2C+Daniel+Keim%2C+and+Mennatallah+El%2DAssady%2E+2023%2E+Rlhf%2Dblender%3A+A+configurable+interactive+interface+for+learning+from+diverse+human+feedback%2E+arXiv+preprint+arX)
16. Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, and Wei Wang. 2023. [Followbench: A multi-level fine-grained constraints following benchmark for large language models](https://md.research.elamur.ai/free/en/papers/jiang-2024-followbench-multi-level-fine-grained/). arXiv preprint arXiv:2310.20410.
17. Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2021. Cross-task generalization via natural language crowdsourcing instructions. arXiv preprint arXiv:2104.08773. [find](https://scholar.google.com/scholar?q=Swaroop+Mishra%2C+Daniel+Khashabi%2C+Chitta+Baral%2C+and+Hannaneh+Hajishirzi%2E+2021%2E+Cross%2Dtask+generalization+via+natural+language+crowdsourcing+instructions%2E+arXiv+preprint+arXiv%3A2104%2E08773%2E)
18. Mandar Joshi, Eunsol Choi, Daniel S Weld, and Luke Zettlemoyer. 2017. [Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/). arXiv preprint arXiv:1705.03551.
19. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 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.
20. Saydulu Kolasani. 2023. Optimizing natural language processing, large language models (llms) for efficient customer service, and hyper-personalization to enable sustainable growth and revenue. Transactions on Latest Trends in Artificial Intelligence, 4(4). [find](https://scholar.google.com/scholar?q=Saydulu+Kolasani%2E+2023%2E+Optimizing+natural+language+processing%2C+large+language+models+%28llms%29+for+efficient+customer+service%2C+and+hyper%2Dpersonalization+to+enable+sustainable+growth+and+revenue%2E+Transac)
21. Nathan Lambert, Louis Castricato, Leandro von Werra, and Alex Havrilla. 2022. Illustrating reinforcement learning from human feedback (rlhf). Hugging Face Blog, 9. [find](https://scholar.google.com/scholar?q=Nathan+Lambert%2C+Louis+Castricato%2C+Leandro+von+Werra%2C+and+Alex+Havrilla%2E+2022%2E+Illustrating+reinforcement+learning+from+human+feedback+%28rlhf%29%2E+Hugging+Face+Blog%2C+9%2E)
22. Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. [The power of scale for parameter-efficient prompt tuning](https://md.research.elamur.ai/free/en/papers/lester-2021-power-scale-parameter-efficient-prompt/). arXiv preprint arXiv:2104.08691.
23. Mukai Li, Shansan Gong, Jiangtao Feng, Yiheng Xu, Jun Zhang, Zhiyong Wu, and Lingpeng Kong. 2023. In-context learning with many demonstration examples. arXiv preprint arXiv:2302.04931. — [arXiv:2302.04931](https://arxiv.org/abs/2302.04931) [find](https://scholar.google.com/scholar?q=Mukai+Li%2C+Shansan+Gong%2C+Jiangtao+Feng%2C+Yiheng+Xu%2C+Jun+Zhang%2C+Zhiyong+Wu%2C+and+Lingpeng+Kong%2E+2023%2E+In%2Dcontext+learning+with+many+demonstration+examples%2E+arXiv+preprint+arXiv%3A2302%2E04931%2E+%E2%80%94+%5BarXiv%3A2302%2E0)
24. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190. [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+arXiv+preprint+arXiv%3A2101%2E00190%2E)
25. Lizi Liao, Grace Hui Yang, and Chirag Shah. 2023. Proactive conversational agents in the post-chatgpt world. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 3452–3455. [find](https://scholar.google.com/scholar?q=Lizi+Liao%2C+Grace+Hui+Yang%2C+and+Chirag+Shah%2E+2023%2E+Proactive+conversational+agents+in+the+post%2Dchatgpt+world%2E+In+Proceedings+of+the+46th+International+ACM+SIGIR+Conference+on+Research+and+Development+i)
26. Na Liu, Liangyu Chen, Xiaoyu Tian, Wei Zou, Kaijiang Chen, and Ming Cui. 2024. From llm to conversational agent: A memory enhanced architecture with fine-tuning of large language models. arXiv preprint arXiv:2401.02777. — [arXiv:2401.02777](https://arxiv.org/abs/2401.02777) [find](https://scholar.google.com/scholar?q=Na+Liu%2C+Liangyu+Chen%2C+Xiaoyu+Tian%2C+Wei+Zou%2C+Kaijiang+Chen%2C+and+Ming+Cui%2E+2024%2E+From+llm+to+conversational+agent%3A+A+memory+enhanced+architecture+with+fine%2Dtuning+of+large+language+models%2E+arXiv+preprin)
27. Renze Lou, Kai Zhang, Jian Xie, Yuxuan Sun, Janice Ahn, Hanzi Xu, Yu Su, and Wenpeng Yin. 2023. Muffin: Curating multi-faceted instructions for improving instruction following. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Renze+Lou%2C+Kai+Zhang%2C+Jian+Xie%2C+Yuxuan+Sun%2C+Janice+Ahn%2C+Hanzi+Xu%2C+Yu+Su%2C+and+Wenpeng+Yin%2E+2023%2E+Muffin%3A+Curating+multi%2Dfaceted+instructions+for+improving+instruction+following%2E+In+The+Twelfth+Internat)
28. OpenAI. 2024. Searchgpt prototype. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Searchgpt+prototype%2E)
29. Yiwei Qin, Kaiqiang Song, Yebowen Hu, Wenlin Yao, Sangwoo Cho, Xiaoyang Wang, Xuansheng Wu, Fei Liu, Pengfei Liu, and Dong Yu. 2024. [Infobench: Evaluating instruction following ability in large language models](https://md.research.elamur.ai/free/en/papers/qin-2024-infobench-evaluating-instruction-following-ability/). arXiv preprint arXiv:2401.03601.
30. Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, et al. 2023. [Code llama: Open foundation models for code](https://md.research.elamur.ai/free/en/papers/roziere-2024-code-llama-open-foundation-models/). arXiv preprint arXiv:2308.12950.
31. Victor Sanh, Albert Webson, Colin Raffel, Stephen H Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, et al. 2021. [Multitask prompted training enables zero-shot task generalization](https://md.research.elamur.ai/free/en/papers/sanh-2021-multitask-prompted-training-enables-zero/). arXiv preprint arXiv:2110.08207.
32. Nisan Stiennon, Long Ouyang, Jeffrey Wu, Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, and Paul F Christiano. 2020. Learning to summarize with human feedback. Advances in Neural Information Processing Systems, 33:3008– 3021. [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+2020%2E+Learning+to+summarize+with+human+feedback%2E+Advances+in+Neural)
33. Zhiqing Sun, Yikang Shen, Qinhong Zhou, Hongxin Zhang, Zhenfang Chen, David Cox, Yiming Yang, and Chuang Gan. 2024. [Principle-driven self-alignment of language models from scratch with minimal human supervision](https://md.research.elamur.ai/free/en/papers/sun-2023-principle-driven-self-alignment-language/). Advances in Neural Information Processing Systems, 36.
34. Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Justin Sun, Xibin Gao, and Yi Zhang. 2024. Bootstrapping llm-based task-oriented dialogue agents via self-talk. arXiv preprint arXiv:2401.05033. [find](https://scholar.google.com/scholar?q=Dennis+Ulmer%2C+Elman+Mansimov%2C+Kaixiang+Lin%2C+Justin+Sun%2C+Xibin+Gao%2C+and+Yi+Zhang%2E+2024%2E+Bootstrapping+llm%2Dbased+task%2Doriented+dialogue+agents+via+self%2Dtalk%2E+arXiv+preprint+arXiv%3A2401%2E05033%2E)
35. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022a. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171.
36. Zihao Zhao, Eric Wallace, Shi Feng, Dan Klein, and Sameer Singh. 2021. [Calibrate before use: Improving few-shot performance of language models](https://md.research.elamur.ai/free/en/papers/zhao-2021-calibrate-before-use-improving-few/). In International conference on machine learning, pages 12697–12706. PMLR.
37. Yizhong Wang, Swaroop Mishra, Pegah Alipoormolabashi, Yeganeh Kordi, Amirreza Mirzaei, Anjana Arunkumar, Arjun Ashok, Arut Selvan Dhanasekaran, Atharva Naik, David Stap, et al. 2022b. Benchmarking generalization via in-context instructions on 1,600+ language tasks. arXiv preprint arXiv:2204.07705, 2… [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+et+al%2E+2022b%2E+Benchmarking+gen)
38. Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, and Le Hou. 2023. [Instruction-following evaluation for large language models](https://md.research.elamur.ai/free/en/papers/zhou-2023-instruction-following-evaluation-large-language/). arXiv preprint arXiv:2311.07911.
39. 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.
40. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837.
41. Daniel M Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B Brown, Alec Radford, Dario Amodei, Paul Christiano, and Geoffrey Irving. 1909. Fine-tuning language models from human preferences. arxiv 2019. arXiv preprint arXiv:1909.08593. [find](https://scholar.google.com/scholar?q=Daniel+M+Ziegler%2C+Nisan+Stiennon%2C+Jeffrey+Wu%2C+Tom+B+Brown%2C+Alec+Radford%2C+Dario+Amodei%2C+Paul+Christiano%2C+and+Geoffrey+Irving%2E+1909%2E+Fine%2Dtuning+language+models+from+human+preferences%2E+arxiv+2019%2E+arXiv)
42. Arkaitz Zubiaga. 2024. Natural language processing in the era of large language models. [find](https://scholar.google.com/scholar?q=Arkaitz+Zubiaga%2E+2024%2E+Natural+language+processing+in+the+era+of+large+language+models%2E)
43. Orion Weller, Nicholas Lourie, Matt Gardner, and Matthew E Peters. 2020. [Learning from task descriptions](https://md.research.elamur.ai/free/en/papers/weller-2020-learning-task-descriptions/). arXiv preprint arXiv:2011.08115.
44. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. 2023. [Autogen: Enabling next-gen llm applications via multi-agent conversation](https://md.research.elamur.ai/free/en/papers/wu-2023-autogen-enabling-next-gen-llm/) framework. arXiv preprint arXiv:2308.08155.
45. Xiaodong Wu, Minhao Wang, Yichen Liu, Xiaoming Shi, He Yan, Xiangju Lu, Junmin Zhu, and Wei Zhang. 2024. [Lifbench: Evaluating the instruction following performance and stability of large language models in long-context scenarios](https://md.research.elamur.ai/free/en/papers/wu-2025-lifbench-evaluating-instruction-following-performance/). arXiv preprint arXiv:2411.07037.
46. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, and Daxin Jiang. 2023. [Wizardlm: Empowering large language models to follow complex instructions](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/). arXiv preprint arXiv:2304.12244.
47. 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)
48. Yifu Yuan, Jianye Hao, Yi Ma, Zibin Dong, Hebin Liang, Jinyi Liu, Zhixin Feng, Kai Zhao, and Yan Zheng. 2024. Uni-rlhf: Universal platform and benchmark suite for reinforcement learning with diverse human feedback. arXiv preprint arXiv:2402.02423. — [arXiv:2402.02423](https://arxiv.org/abs/2402.02423) [find](https://scholar.google.com/scholar?q=Yifu+Yuan%2C+Jianye+Hao%2C+Yi+Ma%2C+Zibin+Dong%2C+Hebin+Liang%2C+Jinyi+Liu%2C+Zhixin+Feng%2C+Kai+Zhao%2C+and+Yan+Zheng%2E+2024%2E+Uni%2Drlhf%3A+Universal+platform+and+benchmark+suite+for+reinforcement+learning+with+diverse+h)
49. Zhiyuan Zeng, Jiatong Yu, Tianyu Gao, Yu Meng, Tanya Goyal, and Danqi Chen. 2023. Evaluating large language models at evaluating instruction following. arXiv preprint arXiv:2310.07641. [find](https://scholar.google.com/scholar?q=Zhiyuan+Zeng%2C+Jiatong+Yu%2C+Tianyu+Gao%2C+Yu+Meng%2C+Tanya+Goyal%2C+and+Danqi+Chen%2E+2023%2E+Evaluating+large+language+models+at+evaluating+instruction+following%2E+arXiv+preprint+arXiv%3A2310%2E07641%2E)

*Updated 1 November 2026*