---
title: "BELLE — paper by Zhang et al. (2025) — summary and ideas"
description: "The authors first examine how question type interacts with method choice. 95% accuracy. 76 references, cited by 6 papers here."
authors: ["Taolin Zhang", "Dongyang Li", "Qizhou Chen", "Chengyu Wang", "Xiaofeng He"]
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.211/"
doi: "10.18653/v1/2025.acl-long.211"
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-belle-bi-level-multi-agent/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2025-belle-bi-level-multi-agent/)

[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/9/) / BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering

# BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering

**Authors:** [Taolin Zhang](https://md.research.elamur.ai/free/en/authors/taolin-zhang/), Dongyang Li, Qizhou Chen, [Chengyu Wang](https://md.research.elamur.ai/free/en/authors/chengyu-wang/) and Xiaofeng He · **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.211/) · [PDF](https://aclanthology.org/2025.acl-long.211.pdf) · [DOI 10.18653/v1/2025.acl-long.211](https://doi.org/10.18653/v1/2025.acl-long.211) · [OpenAlex](https://openalex.org/W4412886695)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [6](https://md.research.elamur.ai/free/en/papers/zhang-2025-belle-bi-level-multi-agent/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Multi-hop question answering requires collecting several pieces of evidence and chaining them together, but existing LLM-based approaches usually apply one fixed strategy to every question. The authors first examine how question type interacts with method choice. Using the native labels of MultiHop-RAG and GPT-4 annotations for 2WikiMultiHopQA, HotPotQA and MuSiQue, they sort questions into Inference, Comparison, Temporal and Null. They then compare CoT, Single-step, Iterative-step, Sub-step and Adaptive-step techniques.

Because each type responds differently to these methods, they design BELLE, which treats every prompting technique as an "operator." After the question is classified, affirmative and negative agents debate before a judge to produce a plan that combines operators. A second level of fast and slow debaters checks whether changes of stance are justified, using both the current exchange and earlier rounds. An executor then carries out the plan.

With GPT-3.5-turbo and Qwen2.5-7B, BELLE outperforms strong baselines on all four datasets. On harder questions it also uses fewer tokens than retrieval-heavy methods, which matters for cost-sensitive QA systems.

## Key points
- **Type annotation:** GPT-4 labeled the unlabeled datasets. Two people independently checked 100 samples per type and accepted prompts only on agreement, reaching 95% accuracy.
- **Combined vs. single operators:** Combinations beat single operators by about 3% on average. Inference questions benefit from decomposition plus iterative retrieval, and Comparison/Temporal questions from decomposition plus single-step retrieval. Null questions can be answered from the model's internal knowledge.
- **Debate dynamics:** Stance shifts are measured with weighted 5×5 operator score matrices (α = β = 0.8, scored by GPT-4). The debate typically settles on operators within about 2 rounds.
- **Efficiency:** BELLE surpasses the previous SOTA BeamAggR in average F1 while needing fewer tokens. Adding more agents does not reliably help and sharply raises token use, and a less confrontational debate setup works better.
- **Limitations:** The iterative multi-agent interaction adds overhead, and the framework may struggle with question formats it has not seen before.

*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
- [East China Normal University](https://md.research.elamur.ai/free/en/universities/east-china-normal-university/) — University, Shanghai, China · 50 works · 2,174 citations
- [Hefei University of Technology](https://md.research.elamur.ai/free/en/universities/hefei-university-of-technology/) — University, Hefei, China · 10 works · 1,615 citations
- [Shanghai University of Electric Power](https://md.research.elamur.ai/free/en/universities/shanghai-university-of-electric-power/) — University, Yangpu, China · 3 works · 13 citations

📚 Shelves (6): [🖥️ 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 · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 441 works

## Cite

Cite as: Taolin Zhang, Dongyang Li, Qizhou Chen, Chengyu Wang and Xiaofeng He. 2025. BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering. 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{zhang2025belle,
  title = {{BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering}},
  author = {Taolin Zhang, Dongyang Li, Qizhou Chen, Chengyu Wang and Xiaofeng He},
  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.211},
  url = {https://doi.org/10.18653/v1/2025.acl-long.211}
}
```

- [← previous AraHalluEval: A Fine-grained Hallucination Evaluation Framework for Arabic LLMs](https://md.research.elamur.ai/free/en/papers/alansari-2025-arahallueval-fine-grained-hallucination-evaluation/)
- [next → Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases](https://md.research.elamur.ai/free/en/papers/hu-2025-between-circuits-chomsky-pre-pretraining/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/9/)

## References

76 references, 27 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Terra Blevins, Hila Gonen, and Luke Zettlemoyer. 2023. Prompting language models for linguistic structure. In ACL, pages 6649–6663. [find](https://scholar.google.com/scholar?q=Terra+Blevins%2C+Hila+Gonen%2C+and+Luke+Zettlemoyer%2E+2023%2E+Prompting+language+models+for+linguistic+structure%2E+In+ACL%2C+pages+6649%E2%80%936663%2E)
2. Angana Borah and Rada Mihalcea. 2024. Towards implicit bias detection and mitigation in multi-agent LLM interactions. In EMNLP, pages 9306–9326. [find](https://scholar.google.com/scholar?q=Angana+Borah+and+Rada+Mihalcea%2E+2024%2E+Towards+implicit+bias+detection+and+mitigation+in+multi%2Dagent+LLM+interactions%2E+In+EMNLP%2C+pages+9306%E2%80%939326%2E)
3. Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego de Las Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Maggiore, Chris Jones, Albin Cas… [find](https://scholar.google.com/scholar?q=Sebastian+Borgeaud%2C+Arthur+Mensch%2C+Jordan+Hoffmann%2C+Trevor+Cai%2C+Eliza+Rutherford%2C+Katie+Millican%2C+George+van+den+Driessche%2C+Jean%2DBaptiste+Lespiau%2C+Bogdan+Damoc%2C+Aidan+Clark%2C+Diego+de+Las+Casas%2C+Aureli)
4. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter,… — [Language Models are Few-Shot Learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
5. Shulin Cao, Jiajie Zhang, Jiaxin Shi, Xin Lv, Zijun Yao, Qi Tian, Lei Hou, and Juanzi Li. 2023. Probabilistic tree-of-thought reasoning for answering knowledge-intensive complex questions. In EMNLP, pages 12541–12560. [find](https://scholar.google.com/scholar?q=Shulin+Cao%2C+Jiajie+Zhang%2C+Jiaxin+Shi%2C+Xin+Lv%2C+Zijun+Yao%2C+Qi+Tian%2C+Lei+Hou%2C+and+Juanzi+Li%2E+2023%2E+Probabilistic+tree%2Dof%2Dthought+reasoning+for+answering+knowledge%2Dintensive+complex+questions%2E+In+EMNLP%2C+p)
6. Edward Y. Chang. 2024. Socrasynth: Multi-llm reasoning with conditional statistics. CoRR, abs/2402.06634. — [arXiv:2402.06634](https://arxiv.org/abs/2402.06634) [find](https://scholar.google.com/scholar?q=Edward+Y%2E+Chang%2E+2024%2E+Socrasynth%3A+Multi%2Dllm+reasoning+with+conditional+statistics%2E+CoRR%2C+abs%2F2402%2E06634%2E+%E2%80%94+%5BarXiv%3A2402%2E06634%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2402%2E06634%29)
7. Wenhu Chen, Hanwen Zha, Zhiyu Chen, Wenhan Xiong, Hong Wang, and William Yang Wang. 2020. [Hybridqa: A dataset of multi-hop question answering over tabular and textual data](https://md.research.elamur.ai/free/en/papers/chen-2020-hybridqa-dataset-multi-hop-question/). In EMNLP, pages 1026– 1036.
8. Zhen Cheng, Jianwei Niu, Shasha Mo, and Jia Chen. 2023. Genboost: Generative modeling and boosted learning for multi-hop question answering over incomplete knowledge graphs. In ICPADS, pages 1131– 1138. [find](https://scholar.google.com/scholar?q=Zhen+Cheng%2C+Jianwei+Niu%2C+Shasha+Mo%2C+and+Jia+Chen%2E+2023%2E+Genboost%3A+Generative+modeling+and+boosted+learning+for+multi%2Dhop+question+answering+over+incomplete+knowledge+graphs%2E+In+ICPADS%2C+pages+1131%E2%80%93+113)
9. Konstantina Christakopoulou, Shibl Mourad, and Maja J. Mataric. 2024. Agents thinking fast and slow: A talker-reasoner architecture. CoRR, abs/2410.08328. — [arXiv:2410.08328](https://arxiv.org/abs/2410.08328) [find](https://scholar.google.com/scholar?q=Konstantina+Christakopoulou%2C+Shibl+Mourad%2C+and+Maja+J%2E+Mataric%2E+2024%2E+Agents+thinking+fast+and+slow%3A+A+talker%2Dreasoner+architecture%2E+CoRR%2C+abs%2F2410%2E08328%2E+%E2%80%94+%5BarXiv%3A2410%2E08328%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F24)
10. Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, and Bing Qin. 2024a. Beamaggr: Beam aggregation reasoning over multi-source knowledge for multi-hop question answering. In ACL, pages 1229–1248. [find](https://scholar.google.com/scholar?q=Zheng+Chu%2C+Jingchang+Chen%2C+Qianglong+Chen%2C+Haotian+Wang%2C+Kun+Zhu%2C+Xiyuan+Du%2C+Weijiang+Yu%2C+Ming+Liu%2C+and+Bing+Qin%2E+2024a%2E+Beamaggr%3A+Beam+aggregation+reasoning+over+multi%2Dsource+knowledge+for+multi%2Dhop+)
11. Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, and Ting Liu. 2024b. Navigate through enigmatic labyrinth A survey of chain of thought reasoning: Advances, frontiers and future. In ACL, pages 1173–1203. [find](https://scholar.google.com/scholar?q=Zheng+Chu%2C+Jingchang+Chen%2C+Qianglong+Chen%2C+Weijiang+Yu%2C+Tao+He%2C+Haotian+Wang%2C+Weihua+Peng%2C+Ming+Liu%2C+Bing+Qin%2C+and+Ting+Liu%2E+2024b%2E+Navigate+through+enigmatic+labyrinth+A+survey+of+chain+of+thought+re)
12. Joost C. F. de Winter, Dimitra Dodou, and Yke Bauke Eisma. 2024. System 2 thinking in openai’s o1-preview model: Near-perfect performance on a mathematics exam. CoRR, abs/2410.07114. [find](https://scholar.google.com/scholar?q=Joost+C%2E+F%2E+de+Winter%2C+Dimitra+Dodou%2C+and+Yke+Bauke+Eisma%2E+2024%2E+System+2+thinking+in+openai%E2%80%99s+o1%2Dpreview+model%3A+Near%2Dperfect+performance+on+a+mathematics+exam%2E+CoRR%2C+abs%2F2410%2E07114%2E)
13. Dheeru Dua, Shivanshu Gupta, Sameer Singh, and Matt Gardner. 2022. Successive prompting for decomposing complex questions. In EMNLP, pages 1251– 1265. [find](https://scholar.google.com/scholar?q=Dheeru+Dua%2C+Shivanshu+Gupta%2C+Sameer+Singh%2C+and+Matt+Gardner%2E+2022%2E+Successive+prompting+for+decomposing+complex+questions%2E+In+EMNLP%2C+pages+1251%E2%80%93+1265%2E)
14. Shangbin Feng, Weijia Shi, Yike Wang, Wenxuan Ding, Vidhisha Balachandran, and Yulia Tsvetkov. 2024. Don’t hallucinate, abstain: Identifying LLM knowledge gaps via multi-llm collaboration. In ACL, pages 14664–14690. [find](https://scholar.google.com/scholar?q=Shangbin+Feng%2C+Weijia+Shi%2C+Yike+Wang%2C+Wenxuan+Ding%2C+Vidhisha+Balachandran%2C+and+Yulia+Tsvetkov%2E+2024%2E+Don%E2%80%99t+hallucinate%2C+abstain%3A+Identifying+LLM+knowledge+gaps+via+multi%2Dllm+collaboration%2E+In+ACL%2C+pag)
15. 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. 2024a. 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)
16. Zeyu He, Chieh-Yang Huang, Chien-Kuang Cornelia Ding, Shaurya Rohatgi, and Ting-Hao Kenneth Huang. 2024b. If in a crowdsourced data annotation pipeline, a GPT-4. In CHI, pages 1040:1–1040:25. [find](https://scholar.google.com/scholar?q=Zeyu+He%2C+Chieh%2DYang+Huang%2C+Chien%2DKuang+Cornelia+Ding%2C+Shaurya+Rohatgi%2C+and+Ting%2DHao+Kenneth+Huang%2E+2024b%2E+If+in+a+crowdsourced+data+annotation+pipeline%2C+a+GPT%2D4%2E+In+CHI%2C+pages+1040%3A1%E2%80%931040%3A25%2E)
17. Zhitao He, Pengfei Cao, Yubo Chen, Kang Liu, Ruopeng Li, Mengshu Sun, and Jun Zhao. 2023. LEGO: A multi-agent collaborative framework with role-playing and iterative feedback for causality explanation generation. In EMNLP, pages 9142–9163. [find](https://scholar.google.com/scholar?q=Zhitao+He%2C+Pengfei+Cao%2C+Yubo+Chen%2C+Kang+Liu%2C+Ruopeng+Li%2C+Mengshu+Sun%2C+and+Jun+Zhao%2E+2023%2E+LEGO%3A+A+multi%2Dagent+collaborative+framework+with+role%2Dplaying+and+iterative+feedback+for+causality+explanation)
18. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. [Constructing A multi-hop QA dataset for comprehensive evaluation of reasoning steps](https://md.research.elamur.ai/free/en/papers/ho-2020-constructing-multi-hop-qa-dataset/). In COLING, pages 6609–6625.
19. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024. [Metagpt: Meta programming for A multi-agent collaborative framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/). In ICLR.
20. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. 2024. [A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions](https://md.research.elamur.ai/free/en/papers/huang-2023-survey-hallucination-large-language-models/). ACM Transactions on Information Systems.
21. Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2022. [Unsupervised dense information retrieval with contrastive learning](https://md.research.elamur.ai/free/en/papers/izacard-2021-unsupervised-dense-information-retrieval-contrastive/). Trans. Mach. Learn. Res.
22. Gautier Izacard, Patrick S. H. Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2023. [Atlas: Few-shot learning with retrieval augmented language models](https://md.research.elamur.ai/free/en/papers/izacard-2022-atlas-few-shot-learning-retrieval/). J. Mach. Learn. Res., 24:251:1–251:43.
23. Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong Park. 2024. [Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity](https://md.research.elamur.ai/free/en/papers/jeong-2024-adaptive-rag-learning-adapt-retrieval/). In NAACL, pages 7036–7050.
24. 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)
25. Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023b. [Active retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/jiang-2023-active-retrieval-augmented-generation/). In EMNLP, pages 7969– 7992.
26. Zhouyu Jiang, Mengshu Sun, Lei Liang, and Zhiqiang Zhang. 2024. Retrieve, summarize, plan: Advancing multi-hop question answering with an iterative approach. CoRR, abs/2407.13101. — [arXiv:2407.13101](https://arxiv.org/abs/2407.13101) [find](https://scholar.google.com/scholar?q=Zhouyu+Jiang%2C+Mengshu+Sun%2C+Lei+Liang%2C+and+Zhiqiang+Zhang%2E+2024%2E+Retrieve%2C+summarize%2C+plan%3A+Advancing+multi%2Dhop+question+answering+with+an+iterative+approach%2E+CoRR%2C+abs%2F2407%2E13101%2E+%E2%80%94+%5BarXiv%3A2407%2E13101%5D)
27. Yimin Jing, Deyi Xiong, and Yan Zhen. 2019. Bi-par: A bilingual parallel dataset for multilingual and cross-lingual reading comprehension on novels. In EMNLP, pages 2452–2462. [find](https://scholar.google.com/scholar?q=Yimin+Jing%2C+Deyi+Xiong%2C+and+Yan+Zhen%2E+2019%2E+Bi%2Dpar%3A+A+bilingual+parallel+dataset+for+multilingual+and+cross%2Dlingual+reading+comprehension+on+novels%2E+In+EMNLP%2C+pages+2452%E2%80%932462%2E)
28. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick S. H. Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. [Dense passage retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/). In EMNLP, pages 6769–6781.
29. Vaibhav Mavi, Anubhav Jangra, and Adam Jatowt. 2022. A survey on multi-hop question answering and generation. CoRR, abs/2204.09140. — [arXiv:2204.09140](https://arxiv.org/abs/2204.09140) [find](https://scholar.google.com/scholar?q=Vaibhav+Mavi%2C+Anubhav+Jangra%2C+and+Adam+Jatowt%2E+2022%2E+A+survey+on+multi%2Dhop+question+answering+and+generation%2E+CoRR%2C+abs%2F2204%2E09140%2E+%E2%80%94+%5BarXiv%3A2204%2E09140%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2204%2E09140%29)
30. Vaibhav Mavi, Anubhav Jangra, and Adam Jatowt. 2024. Multi-hop question answering. Found. Trends Inf. Retr., 17(5):457–586. [find](https://scholar.google.com/scholar?q=Vaibhav+Mavi%2C+Anubhav+Jangra%2C+and+Adam+Jatowt%2E+2024%2E+Multi%2Dhop+question+answering%2E+Found%2E+Trends+Inf%2E+Retr%2E%2C+17%285%29%3A457%E2%80%93586%2E)
31. Sachit Menon, Richard S. Zemel, and Carl Vondrick. 2024. Whiteboard-of-thought: Thinking step-by-step across modalities. In EMNLP, pages 20016–20031. [find](https://scholar.google.com/scholar?q=Sachit+Menon%2C+Richard+S%2E+Zemel%2C+and+Carl+Vondrick%2E+2024%2E+Whiteboard%2Dof%2Dthought%3A+Thinking+step%2Dby%2Dstep+across+modalities%2E+In+EMNLP%2C+pages+20016%E2%80%9320031%2E)
32. Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, and Lu Wang. 2023. Few-shot reranking for multi-hop QA via language model prompting. In ACL, pages 15882–15897. [find](https://scholar.google.com/scholar?q=Muhammad+Khalifa%2C+Lajanugen+Logeswaran%2C+Moontae+Lee%2C+Honglak+Lee%2C+and+Lu+Wang%2E+2023%2E+Few%2Dshot+reranking+for+multi%2Dhop+QA+via+language+model+prompting%2E+In+ACL%2C+pages+15882%E2%80%9315897%2E)
33. Shervin Minaee, Tomás Mikolov, Narjes Nikzad, Meysam Chenaghlu, Richard Socher, Xavier Amatriain, and Jianfeng Gao. 2024. [Large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). CoRR, abs/2402.06196.
34. Akbir Khan, John Hughes, Dan Valentine, Laura Ruis, Kshitij Sachan, Ansh Radhakrishnan, Edward Grefenstette, Samuel R. Bowman, Tim Rocktäschel, and Ethan Perez. 2024. Debating with more persuasive llms leads to more truthful answers. In ICML. [find](https://scholar.google.com/scholar?q=Akbir+Khan%2C+John+Hughes%2C+Dan+Valentine%2C+Laura+Ruis%2C+Kshitij+Sachan%2C+Ansh+Radhakrishnan%2C+Edward+Grefenstette%2C+Samuel+R%2E+Bowman%2C+Tim+Rockt%C3%A4schel%2C+and+Ethan+Perez%2E+2024%2E+Debating+with+more+persuasive+llm)
35. Yee Man Ng and Ilia Markov. 2024. Leveraging open-source large language models for native language identification. CoRR, abs/2409.09659. [find](https://scholar.google.com/scholar?q=Yee+Man+Ng+and+Ilia+Markov%2E+2024%2E+Leveraging+open%2Dsource+large+language+models+for+native+language+identification%2E+CoRR%2C+abs%2F2409%2E09659%2E)
36. Angeliki Lazaridou, Elena Gribovskaya, Wojciech Stokowiec, and Nikolai Grigorev. 2022. [Internet-augmented language models through few-shot prompting for open-domain question answering](https://md.research.elamur.ai/free/en/papers/lazaridou-2022-internet-augmented-language-models-through/). CoRR, abs/2203.05115.
37. Fangyu Lei, Xiang Li, Yifan Wei, Shizhu He, Yiming Huang, Jun Zhao, and Kang Liu. 2023. S3HQA: A three-stage approach for multi-hop text-table hybrid question answering. In EMNLP, pages 1731–1740. [find](https://scholar.google.com/scholar?q=Fangyu+Lei%2C+Xiang+Li%2C+Yifan+Wei%2C+Shizhu+He%2C+Yiming+Huang%2C+Jun+Zhao%2C+and+Kang+Liu%2E+2023%2E+S3HQA%3A+A+three%2Dstage+approach+for+multi%2Dhop+text%2Dtable+hybrid+question+answering%2E+In+EMNLP%2C+pages+1731%E2%80%931740%2E)
38. Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [CAMEL: communicative agents for "mind" exploration of large scale language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). CoRR, abs/2303.17760.
39. Renhao Li, Minghuan Tan, Derek F. Wong, and Min Yang. 2024. Coevol: Constructing better responses for instruction finetuning through multi-agent cooperation. In EMNLP, pages 4703–4721. [find](https://scholar.google.com/scholar?q=Renhao+Li%2C+Minghuan+Tan%2C+Derek+F%2E+Wong%2C+and+Min+Yang%2E+2024%2E+Coevol%3A+Constructing+better+responses+for+instruction+finetuning+through+multi%2Dagent+cooperation%2E+In+EMNLP%2C+pages+4703%E2%80%934721%2E)
40. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2024. [Encouraging divergent thinking in large language models through multi-agent debate](https://md.research.elamur.ai/free/en/papers/liang-2023-encouraging-divergent-thinking-large-language/). In EMNLP, pages 17889–17904.
41. Xi Victoria Lin, Richard Socher, and Caiming Xiong. 2018. Multi-hop knowledge graph reasoning with reward shaping. In EMNLP, pages 3243–3253. [find](https://scholar.google.com/scholar?q=Xi+Victoria+Lin%2C+Richard+Socher%2C+and+Caiming+Xiong%2E+2018%2E+Multi%2Dhop+knowledge+graph+reasoning+with+reward+shaping%2E+In+EMNLP%2C+pages+3243%E2%80%933253%2E)
42. Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. 2023. Dynamic llm-agent network: An llm-agent collaboration framework with agent team optimization. CoRR, abs/2310.02170. [find](https://scholar.google.com/scholar?q=Zijun+Liu%2C+Yanzhe+Zhang%2C+Peng+Li%2C+Yang+Liu%2C+and+Diyi+Yang%2E+2023%2E+Dynamic+llm%2Dagent+network%3A+An+llm%2Dagent+collaboration+framework+with+agent+team+optimization%2E+CoRR%2C+abs%2F2310%2E02170%2E)
43. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In ICLR. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2019%2E+Decoupled+weight+decay+regularization%2E+In+ICLR%2E)
44. Zhengdong Lu, Hang Li, and Ben Kao. 2016. Neural enquirer: learning to query tables in natural language. IEEE Data Eng. Bull., 39(3):63–73. [find](https://scholar.google.com/scholar?q=Zhengdong+Lu%2C+Hang+Li%2C+and+Ben+Kao%2E+2016%2E+Neural+enquirer%3A+learning+to+query+tables+in+natural+language%2E+IEEE+Data+Eng%2E+Bull%2E%2C+39%283%29%3A63%E2%80%9373%2E)
45. OpenAI. 2023. [GPT-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). abs/2303.08774.
46. CoRR, Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A. Smith, and Mike Lewis. 2023. Measuring and narrowing the compositionality gap in language models. In EMNLP, pages 5687–5711. [find](https://scholar.google.com/scholar?q=CoRR%2C+Ofir+Press%2C+Muru+Zhang%2C+Sewon+Min%2C+Ludwig+Schmidt%2C+Noah+A%2E+Smith%2C+and+Mike+Lewis%2E+2023%2E+Measuring+and+narrowing+the+compositionality+gap+in+language+models%2E+In+EMNLP%2C+pages+5687%E2%80%935711%2E)
47. Qwen Team. 2024. Qwen2.5: A party of foundation models. [find](https://scholar.google.com/scholar?q=Qwen+Team%2E+2024%2E+Qwen2%2E5%3A+A+party+of+foundation+models%2E)
48. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. [Squad: 100, 000+ questions for machine comprehension of text](https://md.research.elamur.ai/free/en/papers/rajpurkar-2016-squad-100-000-questions-machine/). In EMNLP, pages 2383–2392.
49. Sumedh Rasal. 2024. LLM harmony: Multi-agent communication for problem solving. CoRR, abs/2401.01312. — [arXiv:2401.01312](https://arxiv.org/abs/2401.01312) [find](https://scholar.google.com/scholar?q=Sumedh+Rasal%2E+2024%2E+LLM+harmony%3A+Multi%2Dagent+communication+for+problem+solving%2E+CoRR%2C+abs%2F2401%2E01312%2E+%E2%80%94+%5BarXiv%3A2401%2E01312%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2401%2E01312%29)
50. Stephen E. Robertson and Hugo Zaragoza. 2009. The probabilistic relevance framework: BM25 and beyond. Found. Trends Inf. Retr., 3(4):333–389. [find](https://scholar.google.com/scholar?q=Stephen+E%2E+Robertson+and+Hugo+Zaragoza%2E+2009%2E+The+probabilistic+relevance+framework%3A+BM25+and+beyond%2E+Found%2E+Trends+Inf%2E+Retr%2E%2C+3%284%29%3A333%E2%80%93389%2E)
51. Omar Shaikh, Hongxin Zhang, William Held, Michael S. Bernstein, and Diyi Yang. 2023. [On second thought, let’s not think step by step!](https://md.research.elamur.ai/free/en/papers/shaikh-2023-second-thought-let-s-not/) bias and toxicity in zero-shot reasoning. In ACL, pages 4454–4470.
52. Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. [Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy](https://md.research.elamur.ai/free/en/papers/shao-2023-enhancing-retrieval-augmented-large-language/). In EMNLP, pages 9248–9274.
53. Zhili Shen, Chenxin Diao, Pavlos Vougiouklis, Pascual Merita, Shriram Piramanayagam, Damien Graux, Dandan Tu, Zeren Jiang, Ruofei Lai, Yang Ren, and Jeff Z. Pan. 2024. Gear: Graph-enhanced agent for retrieval-augmented generation. CoRR, abs/2412.18431. [find](https://scholar.google.com/scholar?q=Zhili+Shen%2C+Chenxin+Diao%2C+Pavlos+Vougiouklis%2C+Pascual+Merita%2C+Shriram+Piramanayagam%2C+Damien+Graux%2C+Dandan+Tu%2C+Zeren+Jiang%2C+Ruofei+Lai%2C+Yang+Ren%2C+and+Jeff+Z%2E+Pan%2E+2024%2E+Gear%3A+Graph%2Denhanced+agent+for+r)
54. Zhengliang Shi, Shuo Zhang, Weiwei Sun, Shen Gao, Pengjie Ren, Zhumin Chen, and Zhaochun Ren. 2024. [Generate-then-ground in retrieval-augmented generation for multi-hop question answering](https://md.research.elamur.ai/free/en/papers/shi-2024-generate-then-ground-retrieval-augmented/). In ACL, pages 7339–7353.
55. Yixuan Tang and Yi Yang. 2024. [Multihop-rag: Benchmarking retrieval-augmented generation for multi-hop queries](https://md.research.elamur.ai/free/en/papers/tang-2024-multihop-rag-benchmarking-retrieval-augmented/). CoRR, abs/2401.15391.
56. Amir Taubenfeld, Yaniv Dover, Roi Reichart, and Ariel Goldstein. 2024. [Systematic biases in LLM simulations of debates](https://md.research.elamur.ai/free/en/papers/taubenfeld-2024-systematic-biases-llm-simulations-debates/). In EMNLP, pages 251–267.
57. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton-Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/)
58. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. Musique: Multi-hop questions via single-hop question composition. Trans. Assoc. Comput. Linguistics, 10:539–554. [find](https://scholar.google.com/scholar?q=Harsh+Trivedi%2C+Niranjan+Balasubramanian%2C+Tushar+Khot%2C+and+Ashish+Sabharwal%2E+2022%2E+Musique%3A+Multi%2Dhop+questions+via+single%2Dhop+question+composition%2E+Trans%2E+Assoc%2E+Comput%2E+Linguistics%2C+10%3A539%E2%80%93554%2E)
59. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2023. [Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions](https://md.research.elamur.ai/free/en/papers/trivedi-2022-interleaving-retrieval-chain-thought-reasoning/). In ACL, pages 10014– 10037.
60. Thomas Walshe, Sae Young Moon, Chunyang Xiao, Yawwani Gunawardana, and Fran Silavong. 2025. Automatic labelling with open-source llms using dynamic label schema integration. Preprint, arXiv:2501.12332. — [arXiv:2501.12332](https://arxiv.org/abs/2501.12332) [find](https://scholar.google.com/scholar?q=Thomas+Walshe%2C+Sae+Young+Moon%2C+Chunyang+Xiao%2C+Yawwani+Gunawardana%2C+and+Fran+Silavong%2E+2025%2E+Automatic+labelling+with+open%2Dsource+llms+using+dynamic+label+schema+integration%2E+Preprint%2C+arXiv%3A2501%2E12332)
61. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 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/). In NeurIPS.
62. Johannes Welbl, Pontus Stenetorp, and Sebastian Riedel. 2018. [Constructing datasets for multi-hop reading comprehension across documents](https://md.research.elamur.ai/free/en/papers/welbl-2018-constructing-datasets-multi-hop-reading/). Trans. Assoc. Comput. Linguistics, 6:287–302.
63. Feijie Wu, Zitao Li, Fei Wei, Yaliang Li, Bolin Ding, and Jing Gao. 2025. Talk to right specialists: Routing and planning in multi-agent system for question answering. Preprint, arXiv:2501.07813. — [arXiv:2501.07813](https://arxiv.org/abs/2501.07813) [find](https://scholar.google.com/scholar?q=Feijie+Wu%2C+Zitao+Li%2C+Fei+Wei%2C+Yaliang+Li%2C+Bolin+Ding%2C+and+Jing+Gao%2E+2025%2E+Talk+to+right+specialists%3A+Routing+and+planning+in+multi%2Dagent+system+for+question+answering%2E+Preprint%2C+arXiv%3A2501%2E07813%2E+%E2%80%94+%5Ba)
64. Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, and Sujian Li. 2024. Watch every step! LLM agent learning via iterative step-level process refinement. In EMNLP, pages 1556–1572. [find](https://scholar.google.com/scholar?q=Weimin+Xiong%2C+Yifan+Song%2C+Xiutian+Zhao%2C+Wenhao+Wu%2C+Xun+Wang%2C+Ke+Wang%2C+Cheng+Li%2C+Wei+Peng%2C+and+Sujian+Li%2E+2024%2E+Watch+every+step%21+LLM+agent+learning+via+iterative+step%2Dlevel+process+refinement%2E+In+EMNL)
65. Ruixin Yang, Dheeraj Rajagopal, Shirley Anugrah Hayati, Bin Hu, and Dongyeop Kang. 2024. Confidence calibration and rationalization for llms via multi-agent deliberation. CoRR, abs/2404.09127. — [arXiv:2404.09127](https://arxiv.org/abs/2404.09127) [find](https://scholar.google.com/scholar?q=Ruixin+Yang%2C+Dheeraj+Rajagopal%2C+Shirley+Anugrah+Hayati%2C+Bin+Hu%2C+and+Dongyeop+Kang%2E+2024%2E+Confidence+calibration+and+rationalization+for+llms+via+multi%2Dagent+deliberation%2E+CoRR%2C+abs%2F2404%2E09127%2E+%E2%80%94+%5BarXi)
66. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. [Hotpotqa: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). In EMNLP, pages 2369–2380.
67. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. In NeurIPS. [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+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+In+NeurIPS%2E)
68. Zhongshen Zeng, Yinhong Liu, Yingjia Wan, Jingyao Li, Pengguang Chen, Jianbo Dai, Yuxuan Yao, Rongwu Xu, Zehan Qi, Wanru Zhao, Linling Shen, Jianqiao Lu, Haochen Tan, Yukang Chen, Hao Zhang, Zhan Shi, Bailin Wang, Zhijiang Guo, and Jiaya Jia. 2024. Mr-ben: A meta-reasoning benchmark for evaluating s… [find](https://scholar.google.com/scholar?q=Zhongshen+Zeng%2C+Yinhong+Liu%2C+Yingjia+Wan%2C+Jingyao+Li%2C+Pengguang+Chen%2C+Jianbo+Dai%2C+Yuxuan+Yao%2C+Rongwu+Xu%2C+Zehan+Qi%2C+Wanru+Zhao%2C+Linling+Shen%2C+Jianqiao+Lu%2C+Haochen+Tan%2C+Yukang+Chen%2C+Hao+Zhang%2C+Zhan+Shi%2C)
69. Bin Zhang, Hangyu Mao, Jingqing Ruan, Ying Wen, Yang Li, Shao Zhang, Zhiwei Xu, Dapeng Li, Ziyue Li, Rui Zhao, Lijuan Li, and Guoliang Fan. 2023. Controlling large language model-based agents for large-scale decision-making: An actor-critic approach. CoRR, abs/2311.13884. — [arXiv:2311.13884](https://arxiv.org/abs/2311.13884) [find](https://scholar.google.com/scholar?q=Bin+Zhang%2C+Hangyu+Mao%2C+Jingqing+Ruan%2C+Ying+Wen%2C+Yang+Li%2C+Shao+Zhang%2C+Zhiwei+Xu%2C+Dapeng+Li%2C+Ziyue+Li%2C+Rui+Zhao%2C+Lijuan+Li%2C+and+Guoliang+Fan%2E+2023%2E+Controlling+large+language+model%2Dbased+agents+for+larg)
70. Taolin Zhang, Qizhou Chen, Dongyang Li, Chengyu Wang, Xiaofeng He, Longtao Huang, Hui Xue’, and Jun Huang. 2024a. Dafnet: Dynamic auxiliary fusion for sequential model editing in large language models. In ACL, pages 1588–1602. [find](https://scholar.google.com/scholar?q=Taolin+Zhang%2C+Qizhou+Chen%2C+Dongyang+Li%2C+Chengyu+Wang%2C+Xiaofeng+He%2C+Longtao+Huang%2C+Hui+Xue%E2%80%99%2C+and+Jun+Huang%2E+2024a%2E+Dafnet%3A+Dynamic+auxiliary+fusion+for+sequential+model+editing+in+large+language+models)
71. Taolin Zhang, Dongyang Li, Qizhou Chen, Chengyu Wang, Longtao Huang, Hui Xue, Xiaofeng He, and Jun Huang. 2024b. R4 : Reinforced retriever-reorder-responder for retrieval-augmented large language models. In ECAI, pages 2314–2321. [find](https://scholar.google.com/scholar?q=Taolin+Zhang%2C+Dongyang+Li%2C+Qizhou+Chen%2C+Chengyu+Wang%2C+Longtao+Huang%2C+Hui+Xue%2C+Xiaofeng+He%2C+and+Jun+Huang%2E+2024b%2E+R4+%3A+Reinforced+retriever%2Dreorder%2Dresponder+for+retrieval%2Daugmented+large+language+mode)
72. Taolin Zhang, Chengyu Wang, Minghui Qiu, Bite Yang, Zerui Cai, Xiaofeng He, and Jun Huang. 2021. Knowledge-empowered representation learning for chinese medical reading comprehension: Task, model and resources. In ACL, pages 2237–2249. [find](https://scholar.google.com/scholar?q=Taolin+Zhang%2C+Chengyu+Wang%2C+Minghui+Qiu%2C+Bite+Yang%2C+Zerui+Cai%2C+Xiaofeng+He%2C+and+Jun+Huang%2E+2021%2E+Knowledge%2Dempowered+representation+learning+for+chinese+medical+reading+comprehension%3A+Task%2C+model+and+)
73. Jun Zhao, Can Zu, Hao Xu, Yi Lu, Wei He, Yiwen Ding, Tao Gui, Qi Zhang, and Xuanjing Huang. 2024. Longagent: Scaling language models to 128k context through multi-agent collaboration. CoRR, abs/2402.11550. — [arXiv:2402.11550](https://arxiv.org/abs/2402.11550) [find](https://scholar.google.com/scholar?q=Jun+Zhao%2C+Can+Zu%2C+Hao+Xu%2C+Yi+Lu%2C+Wei+He%2C+Yiwen+Ding%2C+Tao+Gui%2C+Qi+Zhang%2C+and+Xuanjing+Huang%2E+2024%2E+Longagent%3A+Scaling+language+models+to+128k+context+through+multi%2Dagent+collaboration%2E+CoRR%2C+abs%2F2402%2E1)
74. Zexuan Zhong, Zhengxuan Wu, Christopher D. Manning, Christopher Potts, and Danqi Chen. 2023. Mquake: Assessing knowledge editing in language models via multi-hop questions. In EMNLP, pages 15686–15702. [find](https://scholar.google.com/scholar?q=Zexuan+Zhong%2C+Zhengxuan+Wu%2C+Christopher+D%2E+Manning%2C+Christopher+Potts%2C+and+Danqi+Chen%2E+2023%2E+Mquake%3A+Assessing+knowledge+editing+in+language+models+via+multi%2Dhop+questions%2E+In+EMNLP%2C+pages+15686%E2%80%9315702)
75. Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V. Le, and Ed H. Chi. 2023. [Least-to-most prompting enables complex reasoning in large language models](https://md.research.elamur.ai/free/en/papers/al-2022-least-most-prompting-enables-complex/). In ICLR.
76. Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, and Qi Zhang. 2024. Efficientrag: Efficient retriever for multi-hop question answering. In EMNLP, pages 3392–3411. [find](https://scholar.google.com/scholar?q=Ziyuan+Zhuang%2C+Zhiyang+Zhang%2C+Sitao+Cheng%2C+Fangkai+Yang%2C+Jia+Liu%2C+Shujian+Huang%2C+Qingwei+Lin%2C+Saravan+Rajmohan%2C+Dongmei+Zhang%2C+and+Qi+Zhang%2E+2024%2E+Efficientrag%3A+Efficient+retriever+for+multi%2Dhop+quest)

*Updated 31 October 2026*