---
title: "HiChunk — paper by Lu et al. (2026) — summary and ideas"
description: "They introduce HiCBench, built on OHRBench documents spanning academia, finance, law, manuals… 36 references, cited by 2 papers here."
authors: ["Wensheng Lu", "Keyu Chen", "Zhifeng Shen", "Ruizhi Qiao", "Xing Sun"]
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.1372/"
doi: "10.18653/v1/2026.acl-long.1372"
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/lu-2026-hichunk-evaluating-enhancing-retrieval-augmented/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/lu-2026-hichunk-evaluating-enhancing-retrieval-augmented/)

[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/4/) / HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking

# HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking

**Authors:** Wensheng Lu, [Keyu Chen](https://md.research.elamur.ai/free/en/authors/keyu-chen/), Zhifeng Shen, [Ruizhi Qiao](https://md.research.elamur.ai/free/en/authors/ruizhi-qiao/) and [Xing Sun](https://md.research.elamur.ai/free/en/authors/xing-sun/) · **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.1372/) · [PDF](https://aclanthology.org/2026.acl-long.1372.pdf) · [DOI 10.18653/v1/2026.acl-long.1372](https://doi.org/10.18653/v1/2026.acl-long.1372) · [OpenAlex](https://openalex.org/W4416390973)

**Citations:** 2 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/lu-2026-hichunk-evaluating-enhancing-retrieval-augmented/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
RAG pipelines depend on how documents are split into chunks, yet standard RAG benchmarks reveal little about chunking quality. The authors argue this is because their evidence is sparse: answers usually rest on one or two sentences, so almost any segmentation retrieves them. They introduce HiCBench, built on OHRBench documents spanning academia, finance, law, manuals and other domains. Its documents carry manually annotated multi-level chunk boundaries, and DeepSeek-R1-0528 generated evidence-dense QA pairs that were then filtered for evidence completeness, density and factual consistency. They also propose HiChunk, which fine-tunes an LLM to produce a hierarchical document structure and uses iterative inference for very long inputs. At query time, an Auto-Merge retrieval algorithm adapts chunk granularity to the question. HiCBench separates chunking methods more clearly than existing benchmarks. HiChunk with Auto-Merge improves chunking, retrieval and answer quality over baselines at acceptable runtime. This matters for any RAG application that involves summarization- or enumeration-style questions spread across long, structured documents.

## Key points
- **Evidence sparsity in existing benchmarks:** evidence in OHRBench and GutenQA averages about 1.7 sentences per question (Qasper: 10.5).
- **HiCBench construction:** documents under 4,000 words or over 50 pages were excluded. Three task types are defined:
  - T0: evidence-sparse questions.
  - T1: single-chunk evidence-dense questions, with chunks of 512–4096 tokens.
  - T2: multi-chunk evidence-dense questions, with chunks of 256–2048 tokens.
- **Auto-Merge ablation (Llama3.1-8B on HiCBench):**
  - With full hierarchical chunking, Auto-Merge reaches an ERec of 81.30, up 2.67, and raises Fact-Cov by 5.17.
  - On flat chunkers (SC, LC, HC L1), Auto-Merge adds under 1 ERec point.
- **Fine-tuning vs. few-shot prompting:** the fine-tuned HiChunk (Qwen3-4B base) achieves an overall chunking F1 of 0.545, versus roughly 0.22–0.23 for 1-shot and 3-shot prompting.
- **Limitations and availability:** gains shrink beyond three hierarchy levels because of scarce training data and accumulating errors from lower levels. Code is available at github.com/TencentCloudADP/hichunk.

*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

- [Tencent](https://md.research.elamur.ai/free/en/companies/tencent/) — Company, Shenzhen, China · 134 works · 19,743 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 (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works

## Cite

Cite as: Wensheng Lu, Keyu Chen, Zhifeng Shen, Ruizhi Qiao and Xing Sun. 2026. HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking. 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{lu2026hichunk,
  title = {{HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking}},
  author = {Wensheng Lu, Keyu Chen, Zhifeng Shen, Ruizhi Qiao and Xing Sun},
  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.1372},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1372}
}
```

- [← previous Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence](https://md.research.elamur.ai/free/en/papers/ghasemabadi-2026-guided-gut-efficient-test-time/)
- [next → HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router](https://md.research.elamur.ai/free/en/papers/mei-2026-hiddenguard-fine-grained-safe-generation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/4/)

## References

36 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, and Juanzi Li. 2024. LongBench: A bilingual, multi-task benchmark for long context understanding. In Proceedings of the 62nd Annual Meeting of the Associat… [find](https://scholar.google.com/scholar?q=Yushi+Bai%2C+Xin+Lv%2C+Jiajie+Zhang%2C+Hongchang+Lyu%2C+Jiankai+Tang%2C+Zhidian+Huang%2C+Zhengxiao+Du%2C+Xiao+Liu%2C+Aohan+Zeng%2C+Lei+Hou%2C+Yuxiao+Dong%2C+Jie+Tang%2C+and+Juanzi+Li%2E+2024%2E+LongBench%3A+A+bilingual%2C+multi%2Dtask)
2. Sinchana Ramakanth Bhat, Max Rudat, Jannis Spiek-ermann, and Nicolas Flores-Herr. 2025. Rethinking chunk size for long-document retrieval: A multi-dataset analysis. arXiv preprint arXiv:2505.21700. — [arXiv:2505.21700](https://arxiv.org/abs/2505.21700) [find](https://scholar.google.com/scholar?q=Sinchana+Ramakanth+Bhat%2C+Max+Rudat%2C+Jannis+Spiek%2Dermann%2C+and+Nicolas+Flores%2DHerr%2E+2025%2E+Rethinking+chunk+size+for+long%2Ddocument+retrieval%3A+A+multi%2Ddataset+analysis%2E+arXiv+preprint+arXiv%3A2505%2E21700%2E+%E2%80%94+)
3. Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024a. [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, pages 2318–2335, Ban…
4. Jiawei Chen, Hongyu Lin, Xianpei Han, and Le Sun. 2024b. [Benchmarking large language models in retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/chen-2023-benchmarking-large-language-models-retrieval/). In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 17754–17762.
5. Sangwoo Cho, Kaiqiang Song, Xiaoyang Wang, Fei Liu, and Dong Yu. 2022. Toward unifying text segmentation and long document summarization. arXiv preprint arXiv:2210.16422. [find](https://scholar.google.com/scholar?q=Sangwoo+Cho%2C+Kaiqiang+Song%2C+Xiaoyang+Wang%2C+Fei+Liu%2C+and+Dong+Yu%2E+2022%2E+Toward+unifying+text+segmentation+and+long+document+summarization%2E+arXiv+preprint+arXiv%3A2210%2E16422%2E)
6. Pradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Cohan, Noah A. Smith, and Matt Gardner. 2021. [A dataset of information-seeking questions and answers anchored in research papers](https://md.research.elamur.ai/free/en/papers/dasigi-2021-dataset-information-seeking-questions-answers/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Lan…
7. DeepSeek-AI. 2025. [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/). Preprint, arXiv:2501.12948.
8. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies,…
9. André V. Duarte, João DS Marques, Miguel Graça, Miguel Freire, Lei Li, and Arlindo L. Oliveira. 2024. LumberChunker: Long-form narrative document segmentation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 6473– 6486, Miami, Florida, USA. Association for Computation… [find](https://scholar.google.com/scholar?q=Andr%C3%A9+V%2E+Duarte%2C+Jo%C3%A3o+DS+Marques%2C+Miguel+Gra%C3%A7a%2C+Miguel+Freire%2C+Lei+Li%2C+and+Arlindo+L%2E+Oliveira%2E+2024%2E+LumberChunker%3A+Long%2Dform+narrative+document+segmentation%2E+In+Findings+of+the+Association+for+Compu)
10. 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.
11. Robert Friel, Masha Belyi, and Atindriyo Sanyal. 2024. Ragbench: Explainable benchmark for retrieval-augmented generation systems. arXiv preprint arXiv:2407.11005. — [arXiv:2407.11005](https://arxiv.org/abs/2407.11005) [find](https://scholar.google.com/scholar?q=Robert+Friel%2C+Masha+Belyi%2C+and+Atindriyo+Sanyal%2E+2024%2E+Ragbench%3A+Explainable+benchmark+for+retrieval%2Daugmented+generation+systems%2E+arXiv+preprint+arXiv%3A2407%2E11005%2E+%E2%80%94+%5BarXiv%3A2407%2E11005%5D%28https%3A%2F%2Farxiv%2Eo)
12. Michael Günther, Isabelle Mohr, Daniel James Williams, Bo Wang, and Han Xiao. 2024. Late chunking: contextual chunk embeddings using long-context embedding models. arXiv preprint arXiv:2409.04701. — [arXiv:2409.04701](https://arxiv.org/abs/2409.04701) [find](https://scholar.google.com/scholar?q=Michael+G%C3%BCnther%2C+Isabelle+Mohr%2C+Daniel+James+Williams%2C+Bo+Wang%2C+and+Han+Xiao%2E+2024%2E+Late+chunking%3A+contextual+chunk+embeddings+using+long%2Dcontext+embedding+models%2E+arXiv+preprint+arXiv%3A2409%2E04701%2E+%E2%80%94+%5B)
13. Hangfeng He, Hongming Zhang, and Dan Roth. 2022. Rethinking with retrieval: Faithful large language model inference. arXiv preprint arXiv:2301.00303. [find](https://scholar.google.com/scholar?q=Hangfeng+He%2C+Hongming+Zhang%2C+and+Dan+Roth%2E+2022%2E+Rethinking+with+retrieval%3A+Faithful+large+language+model+inference%2E+arXiv+preprint+arXiv%3A2301%2E00303%2E)
14. Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, and Lu Wang. 2021. [Efficient attentions for long document summarization](https://md.research.elamur.ai/free/en/papers/huang-2021-efficient-attentions-long-document-summarization/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1419–1436, Online.…
15. Arihant Jain, Purav Aggarwal, and Anoop Saladi. 2025. Autochunker: Structured text chunking and its evaluation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 983–995. [find](https://scholar.google.com/scholar?q=Arihant+Jain%2C+Purav+Aggarwal%2C+and+Anoop+Saladi%2E+2025%2E+Autochunker%3A+Structured+text+chunking+and+its+evaluation%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+Linguisti)
16. Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, and Zhicheng Dou. 2025. [Hierarchical document refinement for long-context retrieval-augmented generation](https://md.research.elamur.ai/free/en/papers/jin-2025-hierarchical-document-refinement-long-context/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume…
17. Tomáš Kočiskỳ, Jonathan Schwarz, Phil Blunsom, Chris Dyer, Karl Moritz Hermann, Gábor Melis, and Edward Grefenstette. 2018. [The narrativeqa reading comprehension challenge](https://md.research.elamur.ai/free/en/papers/kocisky-2018-narrativeqa-reading-comprehension-challenge/). Transactions of the Association for Computational Linguistics, 6:317–328.
18. Omri Koshorek, Adir Cohen, Noam Mor, Michael Rotman, and Jonathan Berant. 2018. [Text segmentation as a supervised learning task](https://md.research.elamur.ai/free/en/papers/koshorek-2018-text-segmentation-as-supervised-learning/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers),…
19. 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–…
20. Xianzhi Li, Samuel Chan, Xiaodan Zhu, Yulong Pei, Zhiqiang Ma, Xiaomo Liu, and Sameena Shah. 2023. Are chatgpt and gpt-4 general-purpose solvers for financial text analytics? a study on several typical tasks. arXiv preprint arXiv:2305.05862. [find](https://scholar.google.com/scholar?q=Xianzhi+Li%2C+Samuel+Chan%2C+Xiaodan+Zhu%2C+Yulong+Pei%2C+Zhiqiang+Ma%2C+Xiaomo+Liu%2C+and+Sameena+Shah%2E+2023%2E+Are+chatgpt+and+gpt%2D4+general%2Dpurpose+solvers+for+financial+text+analytics%3F+a+study+on+several+typica)
21. Yang Liu, Chenguang Zhu, and Michael Zeng. 2021. End-to-end segmentation-based news summarization. arXiv preprint arXiv:2110.07850. [find](https://scholar.google.com/scholar?q=Yang+Liu%2C+Chenguang+Zhu%2C+and+Michael+Zeng%2E+2021%2E+End%2Dto%2Dend+segmentation%2Dbased+news+summarization%2E+arXiv+preprint+arXiv%3A2110%2E07850%2E)
22. Tengchao Lv, Lei Cui, Momcilo Vasilijevic, and Furu Wei. 2021. Vt-ssum: A benchmark dataset for video transcript segmentation and summarization. arXiv preprint arXiv:2106.05606. — [arXiv:2106.05606](https://arxiv.org/abs/2106.05606) [find](https://scholar.google.com/scholar?q=Tengchao+Lv%2C+Lei+Cui%2C+Momcilo+Vasilijevic%2C+and+Furu+Wei%2E+2021%2E+Vt%2Dssum%3A+A+benchmark+dataset+for+video+transcript+segmentation+and+summarization%2E+arXiv+preprint+arXiv%3A2106%2E05606%2E+%E2%80%94+%5BarXiv%3A2106%2E05606%5D%28h)
23. Richard Yuanzhe Pang, Alicia Parrish, Nitish Joshi, Nikita Nangia, Jason Phang, Angelica Chen, Vishakh Padmakumar, Johnny Ma, Jana Thompson, He He, and 1 others. 2021. [Quality: Question answering with long input texts, yes!](https://md.research.elamur.ai/free/en/papers/pang-2022-quality-question-answering-long-input/) arXiv preprint arXiv:2112.08608.
24. Saba Sturua, Isabelle Mohr, Mohammad Kalim Akram, Michael Günther, Bo Wang, Markus Krimmel, Feng Wang, Georgios Mastrapas, Andreas Koukounas, Nan Wang, and 1 others. 2024. jina-embeddings-v3: Multilingual embeddings with task lora. arXiv preprint arXiv:2409.10173. [find](https://scholar.google.com/scholar?q=Saba+Sturua%2C+Isabelle+Mohr%2C+Mohammad+Kalim+Akram%2C+Michael+G%C3%BCnther%2C+Bo+Wang%2C+Markus+Krimmel%2C+Feng+Wang%2C+Georgios+Mastrapas%2C+Andreas+Koukounas%2C+Nan+Wang%2C+and+1+others%2E+2024%2E+jina%2Dembeddings%2Dv3%3A+Multilin)
25. Qwen Team. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
26. Cunxiang Wang, Xiaoze Liu, Yuanhao Yue, Xiangru Tang, Tianhang Zhang, Cheng Jiayang, Yunzhi Yao, Wenyang Gao, Xuming Hu, Zehan Qi, and 1 others. 2023. [Survey on factuality in large language models: Knowledge, retrieval and domain-specificity](https://md.research.elamur.ai/free/en/papers/wang-2023-survey-factuality-large-language-models/). arXiv preprint arXiv:2310.07521.
27. Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, and 1 others. 2025. Document segmentation matters for retrieval-augmented generation. In Findings of the Association for Computational Linguistics: ACL 2025, pages 8063… [find](https://scholar.google.com/scholar?q=Zhitong+Wang%2C+Cheng+Gao%2C+Chaojun+Xiao%2C+Yufei+Huang%2C+Shuzheng+Si%2C+Kangyang+Luo%2C+Yuzhuo+Bai%2C+Wenhao+Li%2C+Tangjian+Duan%2C+Chuancheng+Lv%2C+and+1+others%2E+2025%2E+Document+segmentation+matters+for+retrieval%2Daugm)
28. Haoqian Wu, Keyu Chen, Haozhe Liu, Mingchen Zhuge, Bing Li, Ruizhi Qiao, Xiujun Shu, Bei Gan, Liangsheng Xu, Bo Ren, and 1 others. 2023. Newsnet: A novel dataset for hierarchical temporal segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10669–… [find](https://scholar.google.com/scholar?q=Haoqian+Wu%2C+Keyu+Chen%2C+Haozhe+Liu%2C+Mingchen+Zhuge%2C+Bing+Li%2C+Ruizhi+Qiao%2C+Xiujun+Shu%2C+Bei+Gan%2C+Liangsheng+Xu%2C+Bo+Ren%2C+and+1+others%2E+2023%2E+Newsnet%3A+A+novel+dataset+for+hierarchical+temporal+segmentation)
29. Zhishang Xiang, Chuanjie Wu, Qinggang Zhang, Shengyuan Chen, Zijin Hong, Xiao Huang, and Jinsong Su. 2025. When to use graphs in rag: A comprehensive analysis for graph retrieval-augmented generation. arXiv preprint arXiv:2506.05690. — [arXiv:2506.05690](https://arxiv.org/abs/2506.05690) [find](https://scholar.google.com/scholar?q=Zhishang+Xiang%2C+Chuanjie+Wu%2C+Qinggang+Zhang%2C+Shengyuan+Chen%2C+Zijin+Hong%2C+Xiao+Huang%2C+and+Jinsong+Su%2E+2025%2E+When+to+use+graphs+in+rag%3A+A+comprehensive+analysis+for+graph+retrieval%2Daugmented+generation%2E)
30. Shitao Xiao, Zheng Liu, Peitian Zhang, Niklas Muennighoff, Defu Lian, and Jian-Yun Nie. 2024. [C-pack: Packed resources for general chinese embeddings](https://md.research.elamur.ai/free/en/papers/xiao-2023-c-pack-packed-resources/). In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, page 641–649, New York…
31. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018a. [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 236…
32. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018b. [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/). arXiv preprint arXiv:1809.09600.
33. Junyuan Zhang, Qintong Zhang, Bin Wang, Linke Ouyang, Zichen Wen, Ying Li, Ka-Ho Chow, Conghui He, and Wentao Zhang. 2024. Ocr hinders rag: Evaluating the cascading impact of ocr on retrieval-augmented generation. arXiv preprint arXiv:2412.02592. — [arXiv:2412.02592](https://arxiv.org/abs/2412.02592) [find](https://scholar.google.com/scholar?q=Junyuan+Zhang%2C+Qintong+Zhang%2C+Bin+Wang%2C+Linke+Ouyang%2C+Zichen+Wen%2C+Ying+Li%2C+Ka%2DHo+Chow%2C+Conghui+He%2C+and+Wentao+Zhang%2E+2024%2E+Ocr+hinders+rag%3A+Evaluating+the+cascading+impact+of+ocr+on+retrieval%2Daugmente)
34. Qinglin Zhang, Qian Chen, Yali Li, Jiaqing Liu, and Wen Wang. 2021. Sequence model with self-adaptive sliding window for efficient spoken document segmentation. In 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 411–418. IEEE. [find](https://scholar.google.com/scholar?q=Qinglin+Zhang%2C+Qian+Chen%2C+Yali+Li%2C+Jiaqing+Liu%2C+and+Wen+Wang%2E+2021%2E+Sequence+model+with+self%2Dadaptive+sliding+window+for+efficient+spoken+document+segmentation%2E+In+2021+IEEE+Automatic+Speech+Recogniti)
35. Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, and 1 others. 2025. [Siren’s song in the ai ocean: A survey on hallucination in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2023-siren-s-song-ai-ocean/). Computational Linguistics, pages 1–46.
36. Jihao Zhao, Zhiyuan Ji, Zhaoxin Fan, Hanyu Wang, Simin Niu, Bo Tang, Feiyu Xiong, and Zhiyu Li. 2025. MoC: Mixtures of text chunking learners for retrieval-augmented generation system. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… [find](https://scholar.google.com/scholar?q=Jihao+Zhao%2C+Zhiyuan+Ji%2C+Zhaoxin+Fan%2C+Hanyu+Wang%2C+Simin+Niu%2C+Bo+Tang%2C+Feiyu+Xiong%2C+and+Zhiyu+Li%2E+2025%2E+MoC%3A+Mixtures+of+text+chunking+learners+for+retrieval%2Daugmented+generation+system%2E+In+Proceedings+)

*Updated 31 October 2026*