---
title: "IterCOMP — paper by Yun and Kim (2026) — summary and ideas"
description: "The authors present IterCOMP, a training-free, model-agnostic framework that builds the compressed prompt in a… 16.67 EM. 51 references."
authors: ["JungMin Yun", "YoungBin Kim"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1559/"
doi: "10.18653/v1/2026.acl-long.1559"
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/yun-2026-itercomp-reasoning-aware-adaptive-prompt/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yun-2026-itercomp-reasoning-aware-adaptive-prompt/)

[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/37/) / IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering

# IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering

**Authors:** [JungMin Yun](https://md.research.elamur.ai/free/en/authors/jungmin-yun/) and [YoungBin Kim](https://md.research.elamur.ai/free/en/authors/youngbin-kim/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1559/) · [PDF](https://aclanthology.org/2026.acl-long.1559.pdf) · [DOI 10.18653/v1/2026.acl-long.1559](https://doi.org/10.18653/v1/2026.acl-long.1559) · [OpenAlex](https://openalex.org/W7166828916)

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

## Summary
Retrieval-augmented generation for multi-hop question answering often gives the reader LLM long, noisy document sets. This raises cost and latency and can lower accuracy. Most existing prompt compressors judge relevance only against the original question, so they drop bridging facts that become relevant only after earlier reasoning steps. The authors present IterCOMP, a training-free, model-agnostic framework that builds the compressed prompt in a loop:

- Documents are split into evidence segments, which are filtered with a mix of semantic and lexical similarity.
- An LLM then checks whether the kept evidence is enough to answer the question.
- If it is not, the LLM identifies the gap and writes a follow-up question that guides the next filtering round.

Preliminary experiments on MuSiQue confirmed that LLMs can handle both the sufficiency check and gap identification. On MuSiQue, 2WikiMultiHopQA and HotpotQA, IterCOMP beats existing baselines in Exact Match and F1 while using fewer tokens. It also degrades less as the number of reasoning hops grows. This makes it practical for commercial black-box LLM APIs.

## Key points
- **Preliminary analysis.** Used MuSiQue questions with 2–4 hops, 400 per hop length. Sub-question/sub-answer pairs were generated with GPT-4o. Tested models were LLaMA-3.1-8B-Instruct, Mistral-7B-Instruct, GPT-3.5-Turbo and GPT-4o.
- **Ablation on MuSiQue.** The full system reaches 16.67 EM / 27.36 F1 at a compression ratio of 0.14.
  - Removing iterative refinement causes the biggest drop (17.39 F1).
  - No filtering, i.e. no compression, gives 19.92 F1.
  - Removing the answerability check gives 23.63 F1 and longer prompts.
- **Similarity scoring.** Combining semantic and lexical scores beats using either one alone.
- **Relevance threshold.** The filtering percentile works best at k = 90. At k = 95, needed evidence starts to be discarded.
- **Efficiency.** On 500 MuSiQue instances, compression cut reader-side API cost by 75.5–79.4% and sped up inference by 1.13×–2.01×. The tested models were GPT-3.5-Turbo, GPT-4o, Gemini-2.5-Flash, Gemini-2.5-Pro and Claude-4.5.

*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

- [Chung-Ang University](https://md.research.elamur.ai/free/en/universities/chung-ang-university/) — University, Seoul, South Korea · 4 works · 12 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

🧭 Topics (3): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [❓ Question answering](https://md.research.elamur.ai/free/en/topics/question-answering/) · 487 works · [🪶 Efficient models & compression](https://md.research.elamur.ai/free/en/topics/efficient-models/) · 297 works

## Cite

Cite as: JungMin Yun and YoungBin Kim. 2026. IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering. Proceedings of the 64th 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{yun2026itercomp,
  title = {{IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering}},
  author = {JungMin Yun and YoungBin Kim},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1559},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1559}
}
```

- [← previous Iterative Self-Correction for Text-Driven Person Re-Identification with Large Vision-Language Models](https://md.research.elamur.ai/free/en/papers/luo-2026-iterative-self-correction-text-driven/)
- [next → Ithaca Revisited: Benchmarking a Domain-Specific Model for Epigraphy in the Age of LLMs](https://md.research.elamur.ai/free/en/papers/locaputo-2026-ithaca-revisited-benchmarking-domain-specific/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/)

## References

51 references, 28 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774. to compress prompt in natural language formats. In Proceedings of…
2. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. [Self-rag: Learning to retrieve, generate, and critique through self-reflection](https://md.research.elamur.ai/free/en/papers/asai-2023-self-rag-learning-retrieve-generate/). In The Twelfth International Conference on Learning Representations.
3. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv e-prints, pages arXiv–2407.
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. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, Haofen Wang, and 1 others. 2023. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). arXiv preprint arXiv:2312.10997, 2(1):32.
6. Zhiwei Cao, Qian Cao, Yu Lu, Ningxin Peng, Luyang Huang, Shanbo Cheng, and Jinsong Su. 2024. Retaining key information under high compression ratios: Query-guided compressor for LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… [find](https://scholar.google.com/scholar?q=Zhiwei+Cao%2C+Qian+Cao%2C+Yu+Lu%2C+Ningxin+Peng%2C+Luyang+Huang%2C+Shanbo+Cheng%2C+and+Jinsong+Su%2E+2024%2E+Retaining+key+information+under+high+compression+ratios%3A+Query%2Dguided+compressor+for+LLMs%2E+In+Proceedings+o)
7. Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. [M3-embedding: Multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation](https://md.research.elamur.ai/free/en/papers/chen-2024-m3-embedding-multi-linguality/). In Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand. As…
8. Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, and Dongyan Zhao. 2024. xrag: Extreme context compression for retrieval-augmented generation with one token. Advances in Neural Information Processing Systems, 37:109487–109516. [find](https://scholar.google.com/scholar?q=Xin+Cheng%2C+Xun+Wang%2C+Xingxing+Zhang%2C+Tao+Ge%2C+Si%2DQing+Chen%2C+Furu+Wei%2C+Huishuai+Zhang%2C+and+Dongyan+Zhao%2E+2024%2E+xrag%3A+Extreme+context+compression+for+retrieval%2Daugmented+generation+with+one+token%2E+Advanc)
9. Alexis Chevalier, Alexander Wettig, Anirudh Ajith, and Danqi Chen. 2023. [Adapting language models to compress contexts](https://md.research.elamur.ai/free/en/papers/chevalier-2023-adapting-language-models-compress-contexts/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3829–3846, Singapore. Association for Computational Linguistics.
10. Eunseong Choi, Sunkyung Lee, Minjin Choi, Jun Park, and Jongwuk Lee. 2024. From reading to compressing: Exploring the multi-document reader for prompt compression. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14734– 14754, Miami, Florida, USA. Association for Compu… [find](https://scholar.google.com/scholar?q=Eunseong+Choi%2C+Sunkyung+Lee%2C+Minjin+Choi%2C+Jun+Park%2C+and+Jongwuk+Lee%2E+2024%2E+From+reading+to+compressing%3A+Exploring+the+multi%2Ddocument+reader+for+prompt+compression%2E+In+Findings+of+the+Association+for+C)
11. Yu-Neng Chuang, Tianwei Xing, Chia-Yuan Chang, Zirui Liu, Xun Chen, and Xia Hu. 2024. [find](https://scholar.google.com/scholar?q=Yu%2DNeng+Chuang%2C+Tianwei+Xing%2C+Chia%2DYuan+Chang%2C+Zirui+Liu%2C+Xun+Chen%2C+and+Xia+Hu%2E+2024%2E)
12. Learning Tao Ge, Hu Jing, Lei Wang, Xun Wang, Si-Qing Chen, and Furu Wei. 2024. [In-context autoencoder for context compression in a large language model](https://md.research.elamur.ai/free/en/papers/ge-2023-context-autoencoder-context-compression-large/). In The Twelfth International Conference on Learning Representations.
13. 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+)
14. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020a. [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 Proceedings of the 28th International Conference on Computational Linguistics, pages 6609–6625, Barcelona, Spain (Online). International Com…
15. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020b. [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/). arXiv preprint arXiv:2011.01060.
16. Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun Song, SeungYoon Han, and Jong C. Park. 2025. EXIT: Context-aware extractive compression for enhancing retrieval-augmented generation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 4895–4924, Vienna, Austria. Association fo… [find](https://scholar.google.com/scholar?q=Taeho+Hwang%2C+Sukmin+Cho%2C+Soyeong+Jeong%2C+Hoyun+Song%2C+SeungYoon+Han%2C+and+Jong+C%2E+Park%2E+2025%2E+EXIT%3A+Context%2Daware+extractive+compression+for+enhancing+retrieval%2Daugmented+generation%2E+In+Findings+of+the+A)
17. 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)
18. Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2023b. [LLMLingua: Compressing prompts for accelerated inference of large language models](https://md.research.elamur.ai/free/en/papers/jiang-2023-llmlingua-compressing-prompts-accelerated-inference/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13358–13376, Singapore. Association for Comp…
19. Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, and Lili Qiu. 2024. [LongLLMLingua: Accelerating and enhancing LLMs in long context scenarios via prompt compression](https://md.research.elamur.ai/free/en/papers/jiang-2023-longllmlingua-accelerating-enhancing-llms-long/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:…
20. Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023c. [Active retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/jiang-2023-active-retrieval-augmented-generation/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7969–7992, Singapore. Association f…
21. Hoyoun Jung and Kyung-Joong Kim. 2024. Discrete prompt compression with reinforcement learning. IEEE Access, 12:72578–72587. [find](https://scholar.google.com/scholar?q=Hoyoun+Jung+and+Kyung%2DJoong+Kim%2E+2024%2E+Discrete+prompt+compression+with+reinforcement+learning%2E+IEEE+Access%2C+12%3A72578%E2%80%9372587%2E)
22. Hyunwoo Kim, Yoonseo Choi, Taehyun Yang, Honggu Lee, Chaneon Park, Yongju Lee, Jin Young Kim, and Juho Kim. 2024. Using llms to investigate correlations of conversational follow-up queries with user satisfaction. arXiv preprint arXiv:2407.13166. — [arXiv:2407.13166](https://arxiv.org/abs/2407.13166) [find](https://scholar.google.com/scholar?q=Hyunwoo+Kim%2C+Yoonseo+Choi%2C+Taehyun+Yang%2C+Honggu+Lee%2C+Chaneon+Park%2C+Yongju+Lee%2C+Jin+Young+Kim%2C+and+Juho+Kim%2E+2024%2E+Using+llms+to+investigate+correlations+of+conversational+follow%2Dup+queries+with+user+s)
23. Shahar Levy, Nir Mazor, Lihi Shalmon, Michael Hassid, and Gabriel Stanovsky. 2025. More documents, same length: Isolating the challenge of multiple documents in RAG. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 19539–19547, Suzhou, China. Association for Computatio… [find](https://scholar.google.com/scholar?q=Shahar+Levy%2C+Nir+Mazor%2C+Lihi+Shalmon%2C+Michael+Hassid%2C+and+Gabriel+Stanovsky%2E+2025%2E+More+documents%2C+same+length%3A+Isolating+the+challenge+of+multiple+documents+in+RAG%2E+In+Findings+of+the+Association+for)
24. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
25. Yuankai Li, Jia-Chen Gu, Di Wu, Kai-Wei Chang, and Nanyun Peng. 2025a. BRIEF: Bridging retrieval and inference for multi-hop reasoning via compression. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 5449–5470, Albuquerque, New Mexico. Association for Computational Li… [find](https://scholar.google.com/scholar?q=Yuankai+Li%2C+Jia%2DChen+Gu%2C+Di+Wu%2C+Kai%2DWei+Chang%2C+and+Nanyun+Peng%2E+2025a%2E+BRIEF%3A+Bridging+retrieval+and+inference+for+multi%2Dhop+reasoning+via+compression%2E+In+Findings+of+the+Association+for+Computational)
26. Yucheng Li, Bo Dong, Frank Guerin, and Chenghua Lin. 2023. [Compressing context to enhance inference efficiency of large language models](https://md.research.elamur.ai/free/en/papers/li-2023-compressing-context-enhance-inference-efficiency/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 6342–6353, Singapore. Association for Computational Linguistics.
27. Zongqian Li, Yinhong Liu, Yixuan Su, and Nigel Collier. 2025b. Prompt compression for [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), p…
28. Barys Liskavets, Maxim Ushakov, Shuvendu Roy, Mark Klibanov, Ali Etemad, and Shane K Luke. 2025. Prompt compression with context-aware sentence encoding for fast and improved llm inference. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 24595–24604. [find](https://scholar.google.com/scholar?q=Barys+Liskavets%2C+Maxim+Ushakov%2C+Shuvendu+Roy%2C+Mark+Klibanov%2C+Ali+Etemad%2C+and+Shane+K+Luke%2E+2025%2E+Prompt+compression+with+context%2Daware+sentence+encoding+for+fast+and+improved+llm+inference%2E+In+Proceed)
29. Nelson F. Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2024. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). Transactions of the Association for Computational Linguistics, 12:157–173.
30. Jesse Mu, Xiang Li, and Noah Goodman. 2023. [Learning to compress prompts with gist tokens](https://md.research.elamur.ai/free/en/papers/mu-2023-learning-compress-prompts-gist-tokens/). Advances in Neural Information Processing Systems, 36:19327– 19352.
31. Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, and Dongmei Zhang. 2024. [LLMLingua-2: Data distillation for efficient and faithful task-agnostic prompt compression](https://md.research.elamur.ai/free/en/papers/pan-2024-llmlingua-2-data-distillation-efficient/). In Findings of the Associat…
32. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah Smith, and Mike Lewis. 2023. Measuring and narrowing the compositionality gap in language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5687–5711, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ofir+Press%2C+Muru+Zhang%2C+Sewon+Min%2C+Ludwig+Schmidt%2C+Noah+Smith%2C+and+Mike+Lewis%2E+2023%2E+Measuring+and+narrowing+the+compositionality+gap+in+language+models%2E+In+Findings+of+the+Association+for+Computation)
33. Julian Schnitzler, Xanh Ho, Jiahao Huang, Florian Boudin, Saku Sugawara, and Akiko Aizawa. 2024. Morehopqa: More than multi-hop reasoning. arXiv preprint arXiv:2406.13397. — [arXiv:2406.13397](https://arxiv.org/abs/2406.13397) [find](https://scholar.google.com/scholar?q=Julian+Schnitzler%2C+Xanh+Ho%2C+Jiahao+Huang%2C+Florian+Boudin%2C+Saku+Sugawara%2C+and+Akiko+Aizawa%2E+2024%2E+Morehopqa%3A+More+than+multi%2Dhop+reasoning%2E+arXiv+preprint+arXiv%3A2406%2E13397%2E+%E2%80%94+%5BarXiv%3A2406%2E13397%5D%28https%3A%2F)
34. 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 Findings of the Association for Computational Linguistics: EMNLP 2023, pages 9248–9274, Singapore. Association for…
35. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H Chi, Nathanael Schärli, and Denny Zhou. 2023. [Large language models can be easily distracted by irrelevant context](https://md.research.elamur.ai/free/en/papers/shi-2023-large-language-models-easily-distracted/). In International Conference on Machine Learning, pages 31210–31227. PMLR.
36. Kumar Shridhar, Koustuv Sinha, Andrew Cohen, Tianlu Wang, Ping Yu, Ramakanth Pasunuru, Mrinmaya Sachan, Jason Weston, and Asli Celikyilmaz. 2024. The ART of LLM refinement: Ask, refine, and trust. [find](https://scholar.google.com/scholar?q=Kumar+Shridhar%2C+Koustuv+Sinha%2C+Andrew+Cohen%2C+Tianlu+Wang%2C+Ping+Yu%2C+Ramakanth+Pasunuru%2C+Mrinmaya+Sachan%2C+Jason+Weston%2C+and+Asli+Celikyilmaz%2E+2024%2E+The+ART+of+LLM+refinement%3A+Ask%2C+refine%2C+and+trust%2E)
37. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 5872–5883, Mexico City, Mexico. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=In+Proceedings+of+the+2024+Conference+of+the+North+American+Chapter+of+the+Association+for+Computational+Linguistics%3A+Human+Language+Technologies+%28Volume+1%3A+Long+Papers%29%2C+pages+5872%E2%80%935883%2C+Mexico+City%2C)
38. 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/). arXiv preprint arXiv:2401.15391.
39. Bernadette J Tix. 2024. Follow-up questions improve documents generated by large language models. arXiv preprint arXiv:2407.12017. — [arXiv:2407.12017](https://arxiv.org/abs/2407.12017) [find](https://scholar.google.com/scholar?q=Bernadette+J+Tix%2E+2024%2E+Follow%2Dup+questions+improve+documents+generated+by+large+language+models%2E+arXiv+preprint+arXiv%3A2407%2E12017%2E+%E2%80%94+%5BarXiv%3A2407%2E12017%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2407%2E12017%29)
40. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. MuSiQue: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational 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+Transactions+of+the+Association+for+Computational+Li)
41. 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 Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), p…
42. Tu Vu, Mohit Iyyer, Xuezhi Wang, Noah Constant, Jerry Wei, Jason Wei, Chris Tar, Yun-Hsuan Sung, Denny Zhou, Quoc Le, and Thang Luong. 2024. Fresh-LLMs: Refreshing large language models with search engine augmentation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 136… [find](https://scholar.google.com/scholar?q=Tu+Vu%2C+Mohit+Iyyer%2C+Xuezhi+Wang%2C+Noah+Constant%2C+Jerry+Wei%2C+Jason+Wei%2C+Chris+Tar%2C+Yun%2DHsuan+Sung%2C+Denny+Zhou%2C+Quoc+Le%2C+and+Thang+Luong%2E+2024%2E+Fresh%2DLLMs%3A+Refreshing+large+language+models+with+search+en)
43. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William 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 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369…
44. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In The eleventh international conference on learning representations.
45. Chanwoong Yoon, Taewhoo Lee, Hyeon Hwang, Minbyul Jeong, and Jaewoo Kang. 2024. [CompAct: Compressing retrieved documents actively for question answering](https://md.research.elamur.ai/free/en/papers/yoon-2024-compact-compressing-retrieved-documents-actively/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21424–21439, Miami, Florida, USA. Association for…
46. Nan Zhang, Prafulla Kumar Choubey, Alexander Fabbri, Gabriel Bernadett-Shapiro, Rui Zhang, Prasenjit Mitra, Caiming Xiong, and Chien-Sheng Wu. 2025. Sirerag: Indexing similar and related information for multihop reasoning. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Nan+Zhang%2C+Prafulla+Kumar+Choubey%2C+Alexander+Fabbri%2C+Gabriel+Bernadett%2DShapiro%2C+Rui+Zhang%2C+Prasenjit+Mitra%2C+Caiming+Xiong%2C+and+Chien%2DSheng+Wu%2E+2025%2E+Sirerag%3A+Indexing+similar+and+related+information+f)
47. Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, and Wei Hu. 2025. [Mitigating lost-in-retrieval problems in retrieval augmented multi-hop question answering](https://md.research.elamur.ai/free/en/papers/zhu-2025-mitigating-lost-retrieval-problems-retrieval/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 22362–22375, Vienna,…
48. Keheng Wang, Feiyu Duan, Peiguang Li, Sirui Wang, and Xunliang Cai. 2025. [LLMs know what they need: Leveraging a missing information guided framework to empower retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/wang-2025-llms-know-what-they-need/). In Proceedings of the 31st International Conference on Computational Linguistics, pages 2379–2400, Abu Dhab…
49. Graham Wilcock. 2024. Anticipating follow-up questions in exploratory information search. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 103– 109, Kyoto, Japan. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Graham+Wilcock%2E+2024%2E+Anticipating+follow%2Dup+questions+in+exploratory+information+search%2E+In+Proceedings+of+the+25th+Annual+Meeting+of+the+Special+Interest+Group+on+Discourse+and+Dialogue%2C+pages+103%E2%80%93+)
50. Guangzhi Xiong, Qiao Jin, Xiao Wang, Minjia Zhang, Zhiyong Lu, and Aidong Zhang. 2024. Improving retrieval-augmented generation in medicine with iterative follow-up questions. In Biocomputing 2025: Proceedings of the Pacific Symposium, pages 199– 214. World Scientific. [find](https://scholar.google.com/scholar?q=Guangzhi+Xiong%2C+Qiao+Jin%2C+Xiao+Wang%2C+Minjia+Zhang%2C+Zhiyong+Lu%2C+and+Aidong+Zhang%2E+2024%2E+Improving+retrieval%2Daugmented+generation+in+medicine+with+iterative+follow%2Dup+questions%2E+In+Biocomputing+2025%3A+Pr)
51. Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2024. RE-COMP: Improving retrieval-augmented LMs with context compression and selective augmentation. In The Twelfth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Fangyuan+Xu%2C+Weijia+Shi%2C+and+Eunsol+Choi%2E+2024%2E+RE%2DCOMP%3A+Improving+retrieval%2Daugmented+LMs+with+context+compression+and+selective+augmentation%2E+In+The+Twelfth+International+Conference+on+Learning+Repr)

*Updated 2 November 2026*