---
title: "IOPO — paper by Zhang et al. (2025) — summary and ideas"
description: "First, they build TRACE, a benchmark generated automatically from open-source simple instructions. 34 references, cited by 14 papers here."
authors: ["Xinghua Zhang", "Haiyang Yu", "Cheng Fu", "Fei Huang", "Yongbin Li"]
year: 2025
venue: "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2025.acl-long.1079/"
doi: "10.18653/v1/2025.acl-long.1079"
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/zhang-2025-iopo-empowering-llms-complex-instruction/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2025-iopo-empowering-llms-complex-instruction/)

[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/6/) / IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization

# IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization

**Authors:** [Xinghua Zhang](https://md.research.elamur.ai/free/en/authors/xinghua-zhang/), [Haiyang Yu](https://md.research.elamur.ai/free/en/authors/haiyang-yu/), Cheng Fu, [Fei Huang](https://md.research.elamur.ai/free/en/authors/fei-huang/) and [Yongbin Li](https://md.research.elamur.ai/free/en/authors/yongbin-li/) · **Year:** 2025 · **Venue:** [Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2025.acl-long.1079/) · [PDF](https://aclanthology.org/2025.acl-long.1079.pdf) · [DOI 10.18653/v1/2025.acl-long.1079](https://doi.org/10.18653/v1/2025.acl-long.1079) · [OpenAlex](https://openalex.org/W4412944801)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [14](https://md.research.elamur.ai/free/en/papers/zhang-2025-iopo-empowering-llms-complex-instruction/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Existing alignment methods such as DPO compare a preferred and a dispreferred response to the same prompt. When a prompt carries many constraints, this makes it hard for a model to notice which constraints matter. Training resources for this setting are also scarce. The authors address both gaps.

First, they build TRACE, a benchmark generated automatically from open-source simple instructions. It relies on a taxonomy of 5 constraint types and 26 constraint dimensions, created by an LLM and refined by humans. An LLM-driven pipeline adds constraints to each instruction, structures it, filters it for quality, and generates and scores responses.

Second, they propose IOPO (Input-Output Preference Optimization). Beyond learning which response is better, IOPO also contrasts different instructions paired with the same response, which pushes the model to attend to fine-grained constraints in the input.

IOPO outperforms SFT and DPO on both in-domain and out-of-domain tests. Token-matched control experiments indicate the gains come from modelling constraints rather than from extra training data.

## Key points
- TRACE has 120K automatically built training instructions and 1K human-verified evaluation items. Only the evaluation split was manually checked.
- In-domain, IOPO beats SFT by 8.15% and DPO by 2.18%. Out-of-domain, the margins are 5.91% and 2.83%, averaging 7.03% and 2.51%. The conclusion gives a different out-of-domain figure versus DPO (3.13%).
- Out-of-domain evaluation includes IFEval and CFBench. The base models are Qwen2-7B and Llama3.1-8B.
- IOPO's loss uses four input-output combinations. As a result, it needs roughly four times SFT's GPU memory, compared with about twice for DPO. Inference speed is unchanged.
- Code and data are released in the AlibabaResearch DAMO-ConvAI GitHub repository.

*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

- [Alibaba Group](https://md.research.elamur.ai/free/en/companies/alibaba-group/) — Company, Hangzhou, China · 168 works · 15,386 citations
- [Alibaba Group (Cayman Islands)](https://md.research.elamur.ai/free/en/companies/alibaba-group-cayman-islands/) — Company, George Town, Cayman Islands · 32 works · 3,389 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

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

## Cite

Cite as: Xinghua Zhang, Haiyang Yu, Cheng Fu, Fei Huang and Yongbin Li. 2025. IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{zhang2025iopo,
  title = {{IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization}},
  author = {Xinghua Zhang, Haiyang Yu, Cheng Fu, Fei Huang and Yongbin Li},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2025},
  doi = {10.18653/v1/2025.acl-long.1079},
  url = {https://doi.org/10.18653/v1/2025.acl-long.1079}
}
```

- [← previous ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs](https://md.research.elamur.ai/free/en/papers/zhang-2025-icr-probe-tracking-hidden-state/)
- [next → Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition](https://md.research.elamur.ai/free/en/papers/tang-2025-large-language-models-automated-literature/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/)

## References

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

1. Qianyu He, Jie Zeng, Wenhao Huang, Lina Chen, Jin Xiao, Qianxi He, Xunzhe Zhou, Jiaqing Liang, and Yanghua Xiao. 2024b. 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+2024b%2E+Can+large+language+models+understand+real%2Dworld+complex+instructions%3F+In+Proceed)
2. Anthropic. 2024. Claude 3.5 sonnet model card addendum. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2024%2E+Claude+3%2E5+sonnet+model+card+addendum%2E)
3. 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 Jiwoo Hong, Noah Lee, and James Thorne. 2024. ORPO: Monolithic preference optimization without referenc… [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+Jiw)
4. David R. Hunter. 2004. MM algorithms for generalized Bradley-Terry models. The Annals of Statistics, 32(1):384 – 406. [find](https://scholar.google.com/scholar?q=David+R%2E+Hunter%2E+2004%2E+MM+algorithms+for+generalized+Bradley%2DTerry+models%2E+The+Annals+of+Statistics%2C+32%281%29%3A384+%E2%80%93+406%2E)
5. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al. 2024. [Openai o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). arXiv preprint arXiv:2412.16720.
6. Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, and Wei Wang. 2024. Follow-Bench: A multi-level fine-grained constraints following benchmark for large language models. In Proceedings of the 62nd Annual Meeting of the Association for Comput… [find](https://scholar.google.com/scholar?q=Yuxin+Jiang%2C+Yufei+Wang%2C+Xingshan+Zeng%2C+Wanjun+Zhong%2C+Liangyou+Li%2C+Fei+Mi%2C+Lifeng+Shang%2C+Xin+Jiang%2C+Qun+Liu%2C+and+Wei+Wang%2E+2024%2E+Follow%2DBench%3A+A+multi%2Dlevel+fine%2Dgrained+constraints+following+benchmar)
7. Callie Y Kim, Christine P Lee, and Bilge Mutlu. 2024. Understanding large-language model (llm)-powered human-robot interaction. In Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, pages 371–380. [find](https://scholar.google.com/scholar?q=Callie+Y+Kim%2C+Christine+P+Lee%2C+and+Bilge+Mutlu%2E+2024%2E+Understanding+large%2Dlanguage+model+%28llm%29%2Dpowered+human%2Drobot+interaction%2E+In+Proceedings+of+the+2024+ACM%2FIEEE+International+Conference+on+Human%2DRo)
8. Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, and Jie Fu. 2024. CIF-bench: A Chinese instruction-following benchmark for evaluating t… [find](https://scholar.google.com/scholar?q=Yizhi+Li%2C+Ge+Zhang%2C+Xingwei+Qu%2C+Jiali+Li%2C+Zhaoqun+Li%2C+Noah+Wang%2C+Hao+Li%2C+Ruibin+Yuan%2C+Yinghao+Ma%2C+Kai+Zhang%2C+Wangchunshu+Zhou%2C+Yiming+Liang%2C+Lei+Zhang%2C+Lei+Ma%2C+Jiajun+Zhang%2C+Zuowen+Li%2C+Wenhao+Huang%2C+C)
9. Renze Lou, Kai Zhang, and Wenpeng Yin. 2023. A comprehensive survey on instruction following. arXiv preprint arXiv:2303.10475. — [arXiv:2303.10475](https://arxiv.org/abs/2303.10475) [find](https://scholar.google.com/scholar?q=Renze+Lou%2C+Kai+Zhang%2C+and+Wenpeng+Yin%2E+2023%2E+A+comprehensive+survey+on+instruction+following%2E+arXiv+preprint+arXiv%3A2303%2E10475%2E+%E2%80%94+%5BarXiv%3A2303%2E10475%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2303%2E10475%29)
10. Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang. 2024. Wizardcoder: Empowering code large language models with evol-instruct. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Ziyang+Luo%2C+Can+Xu%2C+Pu+Zhao%2C+Qingfeng+Sun%2C+Xiubo+Geng%2C+Wenxiang+Hu%2C+Chongyang+Tao%2C+Jing+Ma%2C+Qingwei+Lin%2C+and+Daxin+Jiang%2E+2024%2E+Wizardcoder%3A+Empowering+code+large+language+models+with+evol%2Dinstruct%2E+I)
11. Yu Meng, Mengzhou Xia, and Danqi Chen. 2024. Simpo: Simple preference optimization with a reference-free reward. In Annual Conference on Neural Information Processing Systems (NeurIPS). [find](https://scholar.google.com/scholar?q=Yu+Meng%2C+Mengzhou+Xia%2C+and+Danqi+Chen%2E+2024%2E+Simpo%3A+Simple+preference+optimization+with+a+reference%2Dfree+reward%2E+In+Annual+Conference+on+Neural+Information+Processing+Systems+%28NeurIPS%29%2E)
12. Swaroop Mishra, Daniel Khashabi, Chitta Baral, and Hannaneh Hajishirzi. 2022. Cross-task generalization via natural language crowdsourcing instructions. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3470–3487. Association fo… [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+In+Proceedings+of+the+60th+Annual+Meeting+of+th)
13. Subhabrata Mukherjee, Arindam Mitra, Ganesh Jawahar, Sahaj Agarwal, Hamid Palangi, and Ahmed Awadallah. 2023. [Orca: Progressive learning from complex explanation traces of gpt-4](https://md.research.elamur.ai/free/en/papers/mukherjee-2023-orca-progressive-learning-complex-explanation/). arXiv preprint arXiv:2306.02707.
14. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll 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 F Christiano, Jan Leike, and Ryan Lowe. 2022. Tra… — [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
15. 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/). In Findings of the Association for Computational Linguistics ACL 2024, pages 13025– 13048…
16. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, 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/). In Advances in Neural Information Processing Systems, volume 36, pages 53728–53741. Curran Associates, Inc.
17. Feifan Song, Bowen Yu, Minghao Li, Haiyang Yu, Fei Huang, Yongbin Li, and Houfeng Wang. 2024. [Preference ranking optimization for human alignment](https://md.research.elamur.ai/free/en/papers/song-2023-preference-ranking-optimization-human-alignment/). In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18990–18998.
18. Haoran Sun, Lixin Liu, Junjie Li, Fengyu Wang, Baohua Dong, Ran Lin, and Ruohui Huang. 2024. [Conifer: Improving complex constrained instruction-following ability of large language models](https://md.research.elamur.ai/free/en/papers/sun-2024-conifer-improving-complex-constrained-instruction/). arXiv preprint arXiv:2404.02823.
19. Minzheng Wang, Longze Chen, Cheng Fu, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, et al. 2024a. [Leave no document behind: Benchmarking long-context llms with extended multi-doc qa](https://md.research.elamur.ai/free/en/papers/wang-2024-leave-no-document-behind-benchmarking/). In EMNLP. Association for Computational Linguistics.
20. Minzheng Wang, Xinghua Zhang, Kun Chen, Nan Xu, Haiyang Yu, Fei Huang, Wenji Mao, and Yongbin Li. 2024b. Reframing dialogue interaction with fine-grained element modeling. arXiv preprint arXiv:2412.04905. — [arXiv:2412.04905](https://arxiv.org/abs/2412.04905) [find](https://scholar.google.com/scholar?q=Minzheng+Wang%2C+Xinghua+Zhang%2C+Kun+Chen%2C+Nan+Xu%2C+Haiyang+Yu%2C+Fei+Huang%2C+Wenji+Mao%2C+and+Yongbin+Li%2E+2024b%2E+Reframing+dialogue+interaction+with+fine%2Dgrained+element+modeling%2E+arXiv+preprint+arXiv%3A2412%2E04)
21. Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, and Zhifang Sui. 2024c. Large language models are not fair evaluators. In Proceedings of ACL, pages 9440–9450. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Peiyi+Wang%2C+Lei+Li%2C+Liang+Chen%2C+Zefan+Cai%2C+Dawei+Zhu%2C+Binghuai+Lin%2C+Yunbo+Cao%2C+Lingpeng+Kong%2C+Qi+Liu%2C+Tianyu+Liu%2C+and+Zhifang+Sui%2E+2024c%2E+Large+language+models+are+not+fair+evaluators%2E+In+Proceedings+)
22. Bosi Wen, Pei Ke, Xiaotao Gu, Lindong Wu, Hao Huang, Jinfeng Zhou, Wenchuang Li, Binxin Hu, Wendy Gao, Jiaxin Xu, Yiming Liu, Jie Tang, Hongning Wang, and Minlie Huang. 2024. Benchmarking complex instruction-following with multiple constraints composition. In Advances in Neural Information Processin… [find](https://scholar.google.com/scholar?q=Bosi+Wen%2C+Pei+Ke%2C+Xiaotao+Gu%2C+Lindong+Wu%2C+Hao+Huang%2C+Jinfeng+Zhou%2C+Wenchuang+Li%2C+Binxin+Hu%2C+Wendy+Gao%2C+Jiaxin+Xu%2C+Yiming+Liu%2C+Jie+Tang%2C+Hongning+Wang%2C+and+Minlie+Huang%2E+2024%2E+Benchmarking+complex+inst)
23. Tingyu Xia, Bowen Yu, Yuan Wu, Yi Chang, and Chang Zhou. 2024. Language models can evaluate themselves via probability discrepancy. In Findings of ACL, pages 4889–4901. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tingyu+Xia%2C+Bowen+Yu%2C+Yuan+Wu%2C+Yi+Chang%2C+and+Chang+Zhou%2E+2024%2E+Language+models+can+evaluate+themselves+via+probability+discrepancy%2E+In+Findings+of+ACL%2C+pages+4889%E2%80%934901%2E+Association+for+Computational+L)
24. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. 2024. [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/). In The Twelfth International Conference on Learning Representations.
25. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024. [Llamafactory: Unified efficient fine-tuning of 100+ language models](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations),…
26. 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.
27. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. 2024a. Qwen2 technical report. arXiv preprint arXiv:2407.10671. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+Chengpeng+Li%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+et+al%2E+2024a%2E+Qwen2+technical+report%2E+arXiv+preprint+arXiv%3A2407%2E10671%2E)
28. Jingfeng Yang, Hongye Jin, Ruixiang Tang, Xiaotian Han, Qizhang Feng, Haoming Jiang, Shaochen Zhong, Bing Yin, and Xia Hu. 2024b. [Harnessing the power of llms in practice: A survey on chatgpt and beyond](https://md.research.elamur.ai/free/en/papers/yang-2023-harnessing-power-llms-practice-survey/). ACM Transactions on Knowledge Discovery from Data, 18(6):1–32.
29. Qinyuan Ye and Xiang Ren. 2021. Learning to generate task-specific adapters from task description. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 646… [find](https://scholar.google.com/scholar?q=Qinyuan+Ye+and+Xiang+Ren%2E+2021%2E+Learning+to+generate+task%2Dspecific+adapters+from+task+description%2E+In+Proceedings+of+the+59th+Annual+Meeting+of+the+Association+for+Computational+Linguistics+and+the+11)
30. Zhiyuan Zeng, Jiatong Yu, Tianyu Gao, Yu Meng, Tanya Goyal, and Danqi Chen. 2024. Evaluating large language models at evaluating instruction following. In Proceedings of ICLR. [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+2024%2E+Evaluating+large+language+models+at+evaluating+instruction+following%2E+In+Proceedings+of+ICLR%2E)
31. Tao Zhang, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, et al. 2024a. [Cfbench: A comprehensive constraints-following benchmark for llms](https://md.research.elamur.ai/free/en/papers/zhang-2025-cfbench-comprehensive-constraints-following-benchmark/). arXiv preprint arXiv:2408.01122.
32. Wenyuan Zhang, Jiawei Sheng, Shuaiyi Nie, Zefeng Zhang, Xinghua Zhang, Yongquan He, and Tingwen Liu. 2024b. Revealing the challenge of detecting character knowledge errors in llm role-playing. arXiv preprint arXiv:2409.11726. — [arXiv:2409.11726](https://arxiv.org/abs/2409.11726) [find](https://scholar.google.com/scholar?q=Wenyuan+Zhang%2C+Jiawei+Sheng%2C+Shuaiyi+Nie%2C+Zefeng+Zhang%2C+Xinghua+Zhang%2C+Yongquan+He%2C+and+Tingwen+Liu%2E+2024b%2E+Revealing+the+challenge+of+detecting+character+knowledge+errors+in+llm+role%2Dplaying%2E+arXiv+p)
33. Xinghua Zhang, Bowen Yu, Haiyang Yu, Yangyu Lv, Tingwen Liu, Fei Huang, Hongbo Xu, and Yongbin Li. 2023. [Wider and deeper llm networks are fairer llm evaluators](https://md.research.elamur.ai/free/en/papers/zhang-2023-wider-deeper-llm-networks-fairer/). Preprint, arXiv:2308.01862.
34. Xinghua Zhang, Haiyang Yu, Yongbin Li, Minzheng Wang, Longze Chen, and Fei Huang. 2024c. The imperative of conversation analysis in the era of llms: A survey of tasks, techniques, and trends. arXiv preprint arXiv:2409.14195. — [arXiv:2409.14195](https://arxiv.org/abs/2409.14195) [find](https://scholar.google.com/scholar?q=Xinghua+Zhang%2C+Haiyang+Yu%2C+Yongbin+Li%2C+Minzheng+Wang%2C+Longze+Chen%2C+and+Fei+Huang%2E+2024c%2E+The+imperative+of+conversation+analysis+in+the+era+of+llms%3A+A+survey+of+tasks%2C+techniques%2C+and+trends%2E+arXiv+pr)

*Updated 30 October 2026*