---
title: "Explain in Your Own Words — paper by Kim and Baek (2026)"
description: "The authors propose TSD-KD, an on-policy, student-centric scheme with three token-selective parts… 41 references, cited by 6 papers here."
authors: ["Minsang Kim", "Seung Jun Baek"]
year: 2026
venue: "arXiv:2603.13260"
source: "https://arxiv.org/abs/2603.13260"
doi: "10.48550/arxiv.2603.13260"
arxiv: "2603.13260"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/kim-2026-explain-own-words-improving-reasoning/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/kim-2026-explain-own-words-improving-reasoning/)

[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/3/) / Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation

# Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation

**Authors:** Minsang Kim and Seung Jun Baek · **Year:** 2026 · **Venue:** arXiv:2603.13260 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2603.13260) · [PDF](https://arxiv.org/pdf/2603.13260) · [DOI 10.48550/arxiv.2603.13260](https://doi.org/10.48550/arxiv.2603.13260) · [arXiv 2603.13260](https://arxiv.org/abs/2603.13260) · [OpenAlex](https://openalex.org/W7138152349)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 6 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Small language models that learn reasoning from larger ones through knowledge distillation (KD) often struggle when made to copy the teacher's full token distribution at every step. A low-capacity student can be overloaded by this, and the gap between teacher and student reasoning styles causes distribution mismatch. The authors propose TSD-KD, an on-policy, student-centric scheme with three token-selective parts:
- **Indirect distillation.** The student proposes its own top-k next-token candidates in the early "opener" segment, where high-entropy branching tokens cluster. The teacher only re-ranks these candidates, and the student learns from that ranking through a Plackett-Luce preference objective.
- **Direct distillation.** A divergence-based loss is restricted to tokens on which the teacher shows high confidence while the student lacks it.
- **Entropy regularization.** Selective entropy minimization keeps the student confident during training.

Across 10 reasoning benchmarks, TSD-KD reports state-of-the-art accuracy and sometimes surpasses the teacher. This suggests that light, targeted guidance can beat full imitation for compressing chain-of-thought reasoning.

## Key points
- Evaluation covers 10 challenging reasoning benchmarks, including math (MATH) and code (MBPP) tasks. The gains reach 54.4% over the baseline student and 40.3% over the second-best method.
- In four cases the distilled student outperformed its own teacher, by as much as 20.3%.
- The preference-based indirect step uses the Plackett-Luce model. The direct step builds on GKD-style generalized JSD, which interpolates between forward and reverse KL.
- In qualitative comparisons against Qwen2.5-1.5B and GKD:
  - TSD-KD correctly converted a string to lower case where both alternatives produced a check function.
  - On a MATH problem, TSD-KD respected a "cents" unit constraint, while GKD collapsed mid-reasoning.
- Code is released at github.com/kmswin1/TSD-KD.

*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

- [Korea University](https://md.research.elamur.ai/free/en/universities/korea-university/) — University, Seoul, South Korea · 26 works · 9,490 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 · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Minsang Kim and Seung Jun Baek. 2026. Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation. arXiv:2603.13260.

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

```bibtex
@misc{kim2026explain,
  title = {{Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation}},
  author = {Minsang Kim and Seung Jun Baek},
  year = {2026},
  doi = {10.48550/arxiv.2603.13260},
  eprint = {2603.13260},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2603.13260}
}
```

- [← previous EVOTOOL: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection](https://md.research.elamur.ai/free/en/papers/yang-2026-evotool-self-evolving-tool-use/)
- [next → Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments](https://md.research.elamur.ai/free/en/papers/ye-2026-feedback-driven-tool-use-improvements/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/)

## References

41 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, Nino Vieillard, Yongchao Zhou, Piotr Stanczyk, Sabela Ramos Garea, Matthieu Geist, and Olivier Bachem. [On-policy distillation of language models: Learning from self-generated mistakes](https://md.research.elamur.ai/free/en/papers/agarwal-2023-policy-distillation-language-models-learning/). In The Twelfth International Conference on Learning Representations, 2024. URL [https://openreview.…](https://openreview.…) [↗](https://openreview.…)
2. Shivam Agarwal, Zimin Zhang, Lifan Yuan, Jiawei Han, and Hao Peng. The unreasonable effectiveness of entropy minimization in llm reasoning. arXiv preprint arXiv:2505.15134, 2025. [find](https://scholar.google.com/scholar?q=Shivam+Agarwal%2C+Zimin+Zhang%2C+Lifan+Yuan%2C+Jiawei+Han%2C+and+Hao+Peng%2E+The+unreasonable+effectiveness+of+entropy+minimization+in+llm+reasoning%2E+arXiv+preprint+arXiv%3A2505%2E15134%2C+2025%2E)
3. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, et al. [Program synthesis with large language models](https://md.research.elamur.ai/free/en/papers/austin-2021-program-synthesis-large-language-models/). arXiv preprint arXiv:2108.07732, 2021.
4. Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. [Curriculum learning](https://md.research.elamur.ai/free/en/papers/bengio-2009-curriculum-learning/). In Proceedings of the 26th annual international conference on machine learning, pp. 41–48, 2009.
5. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, et al. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI conference on artificial int… [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Nils+Blach%2C+Ales+Kubicek%2C+Robert+Gerstenberger%2C+Michal+Podstawski%2C+Lukas+Gianinazzi%2C+Joanna+Gajda%2C+Tomasz+Lehmann%2C+Hubert+Niewiadomski%2C+Piotr+Nyczyk%2C+et+al%2E+Graph+of+thoughts%3A+Solving+el)
6. Ralph Allan Bradley and Milton E Terry. Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39(3/4):324–345, 1952. [find](https://scholar.google.com/scholar?q=Ralph+Allan+Bradley+and+Milton+E+Terry%2E+Rank+analysis+of+incomplete+block+designs%3A+I%2E+the+method+of+paired+comparisons%2E+Biometrika%2C+39%283%2F4%29%3A324%E2%80%93345%2C+1952%2E)
7. Cristian Buciluǎ, Rich Caruana, and Alexandru Niculescu-Mizil. Model compression. In Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 535–541, 2006. [find](https://scholar.google.com/scholar?q=Cristian+Bucilua%CC%8C%2C+Rich+Caruana%2C+and+Alexandru+Niculescu%2DMizil%2E+Model+compression%2E+In+Proceedings+of+the+12th+ACM+SIGKDD+international+conference+on+Knowledge+discovery+and+data+mining%2C+pp%2E+535%E2%80%93541%2C+2)
8. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168, 2021.
9. Kaituo Feng, Changsheng Li, Xiaolu Zhang, Jun Zhou, Ye Yuan, and Guoren Wang. Keypoint-based progressive chain-of-thought distillation for llms. arXiv preprint arXiv:2405.16064, 2024. — [arXiv:2405.16064](https://arxiv.org/abs/2405.16064) [find](https://scholar.google.com/scholar?q=Kaituo+Feng%2C+Changsheng+Li%2C+Xiaolu+Zhang%2C+Jun+Zhou%2C+Ye+Yuan%2C+and+Guoren+Wang%2E+Keypoint%2Dbased+progressive+chain%2Dof%2Dthought+distillation+for+llms%2E+arXiv+preprint+arXiv%3A2405%2E16064%2C+2024%2E+%E2%80%94+%5BarXiv%3A2405%2E16)
10. Yuxian Gu, Li Dong, Furu Wei, and Minlie Huang. Minillm: Knowledge distillation of large language models. arXiv preprint arXiv:2306.[08543, 2023](https://md.research.elamur.ai/free/en/papers/gu-2023-minillm-policy-distillation-large-language/).
11. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948, 2025.
12. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). Proceedings of the International Conference on Learning Representations (ICLR), 2021a.
13. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). NeurIPS, 2021b.
14. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. [Distilling the knowledge in a neural network](https://md.research.elamur.ai/free/en/papers/hinton-2015-distilling-knowledge-neural-network/). arXiv preprint arXiv:1503.02531, 2015.
15. Ferenc Huszár. How (not) to train your generative model: Scheduled sampling, likelihood, adversary? arXiv preprint arXiv:1511.05101, 2015. — [arXiv:1511.05101](https://arxiv.org/abs/1511.05101) [find](https://scholar.google.com/scholar?q=Ferenc+Husz%C3%A1r%2E+How+%28not%29+to+train+your+generative+model%3A+Scheduled+sampling%2C+likelihood%2C+adversary%3F+arXiv+preprint+arXiv%3A1511%2E05101%2C+2015%2E+%E2%80%94+%5BarXiv%3A1511%2E05101%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1511%2E05101%29)
16. Yoon Kim and Alexander M Rush. [Sequence-level knowledge distillation](https://md.research.elamur.ai/free/en/papers/kim-2016-sequence-level-knowledge-distillation/). In Proceedings of the 2016 conference on empirical methods in natural language processing, pp. 1317–1327, 2016.
17. Jongwoo Ko, Sungnyun Kim, Tianyi Chen, and Se-Young Yun. [Distillm: Towards streamlined distillation for large language models](https://md.research.elamur.ai/free/en/papers/ko-2024-distillm-towards-streamlined-distillation-large/). In International Conference on Machine Learning, pp. 24872–24895. PMLR, 2024.
18. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). Advances in neural information processing systems, 35: 22199–22213, 2022.
19. Tuan Anh Le. Reverse vs forward KL, December 2017. URL [https://www.tuananhle.co.uk/notes/reverse-forward-kl.html](https://www.tuananhle.co.uk/notes/reverse-forward-kl.html). Accessed: 2025-09-22. [↗](https://www.tuananhle.co.uk/notes/reverse-forward-kl.html)
20. Qintong Li, Leyang Cui, Xueliang Zhao, Lingpeng Kong, and Wei Bi. [Gsm-plus: A comprehensive benchmark for evaluating the robustness of llms as mathematical problem solvers](https://md.research.elamur.ai/free/en/papers/li-2024-gsm-plus-comprehensive-benchmark-evaluating/). arXiv preprint arXiv:2402.19255, 2024.
21. Alexander Lin, Jeremy Wohlwend, Howard Chen, and Tao Lei. Autoregressive knowledge distillation through imitation learning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6121–6133, 2020. [find](https://scholar.google.com/scholar?q=Alexander+Lin%2C+Jeremy+Wohlwend%2C+Howard+Chen%2C+and+Tao+Lei%2E+Autoregressive+knowledge+distillation+through+imitation+learning%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Langua)
22. Rafael Müller, Simon Kornblith, and Geoffrey E Hinton. When does label smoothing help? Advances in neural information processing systems, 32, 2019. [find](https://scholar.google.com/scholar?q=Rafael+M%C3%BCller%2C+Simon+Kornblith%2C+and+Geoffrey+E+Hinton%2E+When+does+label+smoothing+help%3F+Advances+in+neural+information+processing+systems%2C+32%2C+2019%2E)
23. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. [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, 2022.
24. Robin L Plackett. The analysis of permutations. Journal of the Royal Statistical Society Series C: Applied Statistics, 24(2):193–202, 1975. [find](https://scholar.google.com/scholar?q=Robin+L+Plackett%2E+The+analysis+of+permutations%2E+Journal+of+the+Royal+Statistical+Society+Series+C%3A+Applied+Statistics%2C+24%282%29%3A193%E2%80%93202%2C+1975%2E)
25. A Yang Qwen, Baosong Yang, B Zhang, B Hui, B Zheng, B Yu, Chengpeng Li, D Liu, F Huang, H Wei, et al. Qwen2. 5 technical report. arXiv preprint, 2024. [find](https://scholar.google.com/scholar?q=A+Yang+Qwen%2C+Baosong+Yang%2C+B+Zhang%2C+B+Hui%2C+B+Zheng%2C+B+Yu%2C+Chengpeng+Li%2C+D+Liu%2C+F+Huang%2C+H+Wei%2C+et+al%2E+Qwen2%2E+5+technical+report%2E+arXiv+preprint%2C+2024%2E)
26. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in neural information processing systems, 36:53728–53741, 2023.
27. Stéphane Ross, Geoffrey Gordon, and Drew Bagnell. A reduction of imitation learning and structured prediction to no-regret online learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp. 627–635. JMLR Workshop and Conference Proceedings, 2011… [find](https://scholar.google.com/scholar?q=St%C3%A9phane+Ross%2C+Geoffrey+Gordon%2C+and+Drew+Bagnell%2E+A+reduction+of+imitation+learning+and+structured+prediction+to+no%2Dregret+online+learning%2E+In+Proceedings+of+the+fourteenth+international+conference+on)
28. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. [Scaling llm test-time compute optimally can be more effective than scaling model parameters](https://md.research.elamur.ai/free/en/papers/snell-2024-scaling-llm-test-time-compute/). arXiv preprint arXiv:2408.03314, 2024.
29. Zayne Rea Sprague, Xi Ye, Kaj Bostrom, Swarat Chaudhuri, and Greg Durrett. MuSR: Testing the limits of chain-of-thought with multistep soft reasoning. In The Twelfth International Conference on Learning Representations, 2024. URL [https://openreview.net/forum?id=jeny](https://openreview.net/forum?id=jeny) YQzue1. [↗](https://openreview.net/forum?id=jeny)
30. Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V Le, Ed H Chi, Denny Zhou, , and Jason Wei. [Challenging big-bench tasks and whether chain-of-thought can solve them](https://md.research.elamur.ai/free/en/papers/suzgun-2023-challenging-big-bench-tasks-whether/). arXiv preprint arXiv:2210.09261, 2022.
31. Jiaxi Tang, Rakesh Shivanna, Zhe Zhao, Dong Lin, Anima Singh, Ed H Chi, and Sagar Jain. Understanding and improving knowledge distillation. arXiv preprint arXiv:2002.03532, 2020. — [arXiv:2002.03532](https://arxiv.org/abs/2002.03532) [find](https://scholar.google.com/scholar?q=Jiaxi+Tang%2C+Rakesh+Shivanna%2C+Zhe+Zhao%2C+Dong+Lin%2C+Anima+Singh%2C+Ed+H+Chi%2C+and+Sagar+Jain%2E+Understanding+and+improving+knowledge+distillation%2E+arXiv+preprint+arXiv%3A2002%2E03532%2C+2020%2E+%E2%80%94+%5BarXiv%3A2002%2E03532%5D%28)
32. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, et al. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:2408.00118, 2024. [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Morgane+Riviere%2C+Shreya+Pathak%2C+Pier+Giuseppe+Sessa%2C+Cassidy+Hardin%2C+Surya+Bhupatiraju%2C+L%C3%A9onard+Hussenot%2C+Thomas+Mesnard%2C+Bobak+Shahriari%2C+Alexandre+Ram%C3%A9%2C+et+al%2E+Gemma+2%3A+Improving+open+la)
33. Shenzhi Wang, Le Yu, Chang Gao, Chujie Zheng, Shixuan Liu, Rui Lu, Kai Dang, Xionghui Chen, Jianxin Yang, Zhenru Zhang, et al. [Beyond the 80/20 rule: High-entropy minority tokens drive effective reinforcement learning for llm reasoning](https://md.research.elamur.ai/free/en/papers/wang-2025-80-20-rule-high-entropy/). arXiv preprint arXiv:2506.01939, 2025.
34. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, et al. [Mmlu-pro: A more robust and challenging multi-task language understanding benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-mmlu-pro-more-robust-challenging/). Advances in Neural Information Processing Systems, 37: 95266–95290, 2024.
35. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. [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, 2022.
36. Johannes Welbl, Nelson F Liu, and Matt Gardner. [Crowdsourcing multiple choice science questions](https://md.research.elamur.ai/free/en/papers/welbl-2017-crowdsourcing-multiple-choice-science-questions/). arXiv preprint arXiv:1707.06209, 2017.
37. Wenda Xu, Rujun Han, Zifeng Wang, Long Le, Dhruv Madeka, Lei Li, William Yang Wang, Rishabh Agarwal, Chen-Yu Lee, and Tomas Pfister. [Speculative knowledge distillation: Bridging the teacher-student gap through interleaved sampling](https://md.research.elamur.ai/free/en/papers/xu-2024-speculative-knowledge-distillation-bridging-teacher/). In The Thirteenth International Conference on Learning Representatio…
38. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388, 2025.
39. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, 36:11809–11822, 2023. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Advances+in+neural+informati)
40. Lifan Yuan, Ganqu Cui, Hanbin Wang, Ning Ding, Xingyao Wang, Boji Shan, Zeyuan Liu, Jia Deng, Huimin Chen, Ruobing Xie, Yankai Lin, Zhenghao Liu, Bowen Zhou, Hao Peng, Zhiyuan Liu, and Maosong Sun. Advancing LLM reasoning generalists with preference trees. In The Thirteenth International Conference… [find](https://scholar.google.com/scholar?q=Lifan+Yuan%2C+Ganqu+Cui%2C+Hanbin+Wang%2C+Ning+Ding%2C+Xingyao+Wang%2C+Boji+Shan%2C+Zeyuan+Liu%2C+Jia+Deng%2C+Huimin+Chen%2C+Ruobing+Xie%2C+Yankai+Lin%2C+Zhenghao+Liu%2C+Bowen+Zhou%2C+Hao+Peng%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+Ad)
41. Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, and Le Hou. [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, 2023.

*Updated 30 October 2026*