---
title: "Pandora's Box or Aladdin's Lamp — paper by Wu et al. (2025)"
description: "This paper builds a broader picture. 59 references, cited by 12 papers here. Among them: 7."
authors: ["Jinyang Wu", "Shuai Zhang", "Feihu Che", "Mingkuan Feng", "Pengpeng Shao", "Jianhua Tao"]
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.250/"
doi: "10.18653/v1/2025.acl-long.250"
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/wu-2025-pandora-s-box-or-aladdin/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2025-pandora-s-box-or-aladdin/)

[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/5/) / Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models

# Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models

**Authors:** [Jinyang Wu](https://md.research.elamur.ai/free/en/authors/jinyang-wu/), [Shuai Zhang](https://md.research.elamur.ai/free/en/authors/shuai-zhang/), [Feihu Che](https://md.research.elamur.ai/free/en/authors/feihu-che/), [Mingkuan Feng](https://md.research.elamur.ai/free/en/authors/mingkuan-feng/), Pengpeng Shao and [Jianhua Tao](https://md.research.elamur.ai/free/en/authors/jianhua-tao/) · **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.250/) · [PDF](https://aclanthology.org/2025.acl-long.250.pdf) · [DOI 10.18653/v1/2025.acl-long.250](https://doi.org/10.18653/v1/2025.acl-long.250) · [OpenAlex](https://openalex.org/W4412886660)

**Citations:** 7 citations (OpenAlex, 2026-10-14) · [12](https://md.research.elamur.ai/free/en/papers/wu-2025-pandora-s-box-or-aladdin/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
RAG is widely used to reduce LLM hallucinations, but real retrieval results are messy. Earlier robustness studies looked at only a few noise types, usually three or fewer, and assumed noise always hurts. This paper builds a broader picture. It defines seven retrieval noise types grounded in linguistics and releases NoiserBench, a benchmark spanning several datasets and reasoning tasks. The benchmark is built in four steps: QA pairs are collected or generated and filtered with ChatGPT plus manual checks, evidence is verified with an NLI model, noisy documents are produced with tools such as search engines, and answers are converted to multiple-choice for automatic zero-shot scoring. Eight LLMs of varied architectures and sizes were evaluated. The noise types fall into two practical groups. Harmful noise lowers accuracy, while beneficial noise improves it. The authors attribute these gains to clearer reasoning, more consistent answer formats, and greater confidence when golden context is present. The work matters for designing RAG systems that suppress damaging noise and possibly exploit helpful noise.

## Key points
- Seven noise types are defined. The beneficial ones are semantic (SeN), datatype (DN: text, URLs, code mixed together) and illegal sentence (ISN). The harmful ones are counterfactual (CN), supportive (SuN), orthographic (ON) and prior (PN, questions built on false premises).
- Evidence quality is checked with bart-large-mnli-407M, which confirms that the evidence entails the answer.
- Adding ISN raised accuracy by more than 10% on average when combined with harmful noise such as counterfactual. It also helped consistently under orthographic noise ratios from 0 to 0.4.
- Wilcoxon signed-rank tests on Llama3-8B-Instruct and Qwen2-7B-Instruct gave p-values below 0.05 for both ISN and DN (e.g., 4.10e-5).
- In a manual review of 100 samples per dataset across seven datasets, beneficial noise produced clearer reasoning in 37 cases versus 31 without it, and better formatting in 26 versus 23. Code: github.com/jinyangwu/NoiserBench.

*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

- [Tsinghua University](https://md.research.elamur.ai/free/en/universities/tsinghua-university/) — University, Beijing, China · 415 works · 94,028 citations
- [Beijing National Research Center for Information Science and Technology](https://md.research.elamur.ai/free/en/labs/beijing-national-research-center-for-information-science-and-technology/) — Research institute, Beijing, China · 33 works · 6,706 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 (1): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works

## Cite

Cite as: Jinyang Wu, Shuai Zhang, Feihu Che, Mingkuan Feng, Pengpeng Shao and Jianhua Tao. 2025. Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models. 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{wu2025pandora,
  title = {{Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models}},
  author = {Jinyang Wu, Shuai Zhang, Feihu Che, Mingkuan Feng, Pengpeng Shao and Jianhua Tao},
  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.250},
  url = {https://doi.org/10.18653/v1/2025.acl-long.250}
}
```

- [← previous NRC VAD Lexicon v2: Norms for Valence, Arousal, and Dominance for over 55k English Terms](https://md.research.elamur.ai/free/en/papers/mohammad-2025-nrc-vad-lexicon-v2-norms/)
- [next → RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions](https://md.research.elamur.ai/free/en/papers/liu-2025-rag-instruct-boosting-llms-diverse/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/5/)

## References

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

1. Aliaa Aloufi. 2021. Language and linguistic orthography. English Language and Literature Studies, 11(3). [find](https://scholar.google.com/scholar?q=Aliaa+Aloufi%2E+2021%2E+Language+and+linguistic+orthography%2E+English+Language+and+Literature+Studies%2C+11%283%29%2E)
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. Sébastien Bubeck, Varun Chadrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al. 2023. [Sparks of artificial general intelligence: Early experiments with gpt-4](https://md.research.elamur.ai/free/en/papers/bubeck-2023-sparks-artificial-general-intelligence-early/). arXiv preprint arXiv:2303.12712.
4. Wallace L Chafe. 1971. Linguistics and human knowledge. Monograph series on languages and linguistics, (24):57. [find](https://scholar.google.com/scholar?q=Wallace+L+Chafe%2E+1971%2E+Linguistics+and+human+knowledge%2E+Monograph+series+on+languages+and+linguistics%2C+%2824%29%3A57%2E)
5. Jiawei Chen, Hongyu Lin, Xianpei Han, and Le Sun. 2024. [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, pages 17754–17762. AAAI Press.
6. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. [https://lmsys.org/blog/](https://lmsys.org/blog/) 2023-03-30-vicuna/. [↗](https://lmsys.org/blog/)
7. Florin Cuconasu, Giovanni Trappolini, Federico Siciliano, Simone Filice, Cesare Campagnano, Yoelle Maarek, et al. 2024. [The power of noise: Redefining retrieval for rag systems](https://md.research.elamur.ai/free/en/papers/cuconasu-2024-power-noise-redefining-retrieval-rag/). In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages…
8. Feiteng Fang, Yuelin Bai, Shiwen Ni, Min Yang, Xiaojun Chen, and Ruifeng Xu. 2024. [Enhancing noise robustness of retrieval-augmented language models with adaptive adversarial training](https://md.research.elamur.ai/free/en/papers/fang-2024-enhancing-noise-robustness-retrieval-augmented/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
9. Gary Feng and Li Yi. 2006. What if chinese had linguistic markers for counterfactual conditionals? language and thought revisited. In Proceedings of the Annual Meeting of the Cognitive Science Society, volume 28. [find](https://scholar.google.com/scholar?q=Gary+Feng+and+Li+Yi%2E+2006%2E+What+if+chinese+had+linguistic+markers+for+counterfactual+conditionals%3F+language+and+thought+revisited%2E+In+Proceedings+of+the+Annual+Meeting+of+the+Cognitive+Science+Society)
10. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 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.
11. 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+)
12. Yves Grandvalet, Stéphane Canu, and Stéphane Boucheron. 1997. Noise injection: Theoretical prospects. Neural Computation, 9(5):1093–1108. [find](https://scholar.google.com/scholar?q=Yves+Grandvalet%2C+St%C3%A9phane+Canu%2C+and+St%C3%A9phane+Boucheron%2E+1997%2E+Noise+injection%3A+Theoretical+prospects%2E+Neural+Computation%2C+9%285%29%3A1093%E2%80%931108%2E)
13. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. 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/). arXiv preprint arXiv:2501.12948.
14. Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. 2025. [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, 43(2):…
15. 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/). Transactions on Machine Learning Research.
16. Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy, Jannik Strötgen, and Gerhard Weikum. 2018. Tempquestions: A benchmark for temporal question answering. In Companion Proceedings of the The Web Conference 2018, pages 1057–1062, Republic and Canton of Geneva, CHE. International World Wide Web Conferen… [find](https://scholar.google.com/scholar?q=Zhen+Jia%2C+Abdalghani+Abujabal%2C+Rishiraj+Saha+Roy%2C+Jannik+Str%C3%B6tgen%2C+and+Gerhard+Weikum%2E+2018%2E+Tempquestions%3A+A+benchmark+for+temporal+question+answering%2E+In+Companion+Proceedings+of+the+The+Web+Confere)
17. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, et al. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825. [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+et+al%2E+2023%2E+Mistral+7b%2E+arXiv+preprint+arXiv%3A2310%2E06825%2E)
18. Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088. [find](https://scholar.google.com/scholar?q=Albert+Q+Jiang%2C+Alexandre+Sablayrolles%2C+Antoine+Roux%2C+Arthur+Mensch%2C+Blanche+Savary%2C+Chris+Bamford%2C+Devendra+Singh+Chaplot%2C+Diego+de+las+Casas%2C+Emma+Bou+Hanna%2C+Florian+Bressand%2C+et+al%2E+2024%2E+Mixtral+o)
19. Nikhil Kandpal, Haikang Deng, Adam Roberts, Eric Wallace, and Colin Raffel. 2023. [Large language models struggle to learn long-tail knowledge](https://md.research.elamur.ai/free/en/papers/kandpal-2022-large-language-models-struggle-learn/). In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 15696–15707. PMLR.
20. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick 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 Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Onli…
21. András Kertész and Csilla Rákosi. 2012. Data and evidence in linguistics: A plausible argumentation model. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Andr%C3%A1s+Kert%C3%A9sz+and+Csilla+R%C3%A1kosi%2E+2012%2E+Data+and+evidence+in+linguistics%3A+A+plausible+argumentation+model%2E+Cambridge+University+Press%2E)
22. Samuel Kotz and Norman L. Johnson, editors. 1992. Breakthroughs in Statistics: Methodology and Distribution. Springer New York, New York, NY. [find](https://scholar.google.com/scholar?q=Samuel+Kotz+and+Norman+L%2E+Johnson%2C+editors%2E+1992%2E+Breakthroughs+in+Statistics%3A+Methodology+and+Distribution%2E+Springer+New+York%2C+New+York%2C+NY%2E)
23. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al. 2019. [Natural questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Linguistic…
24. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020a. [BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension](https://md.research.elamur.ai/free/en/papers/lewis-2020-bart-denoising-sequence-sequence-pre/). In Proceedings of the 58th Annual Meeting of th…
25. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2020b. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). In Advances in Neural Information Pro…
26. Meta, AI. 2024. Introducing meta llama 3: The most capable openly available llm to date. [https://ai.meta.com/blog/meta-llama-3/](https://ai.meta.com/blog/meta-llama-3/). [↗](https://ai.meta.com/blog/meta-llama-3/)
27. Femi Olan, Uchitha Jayawickrama, Emmanuel Ogiem-wonyi Arakpogun, Jana Suklan, and Shaofeng Liu. 2024. Fake news on social media: the impact on society. Information Systems Frontiers, 26(2):443–458. [find](https://scholar.google.com/scholar?q=Femi+Olan%2C+Uchitha+Jayawickrama%2C+Emmanuel+Ogiem%2Dwonyi+Arakpogun%2C+Jana+Suklan%2C+and+Shaofeng+Liu%2E+2024%2E+Fake+news+on+social+media%3A+the+impact+on+society%2E+Information+Systems+Frontiers%2C+26%282%29%3A443%E2%80%93458%2E)
28. OpenAI. 2023. Introducing chatgpt. [https://openai.com/index/chatgpt/](https://openai.com/index/chatgpt/). [↗](https://openai.com/index/chatgpt/)
29. Preligens Lab. 2023. Textnoisr: Adding random noise to a dataset. [https://github.com/](https://github.com/) preligens-lab/textnoisr. [↗](https://github.com/)
30. 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)
31. Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2021. [RocketQA: An optimized training approach to dense passage retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/qu-2021-rocketqa-optimized-training-approach-dense/). In Proceedings of the 2021 Conference of the North American Chapter of the Ass…
32. Ishith Seth, Bryan Lim, Yi Xie, Jevan Cevik, Warren M Rozen, Richard J Ross, and Mathew Lee. 2023. Comparing the efficacy of large language models Chat-GPT, BARD, and Bing AI in providing information on rhinoplasty: an observational study. Aesthetic Surgery Journal Open Forum, 5:ojad084. [find](https://scholar.google.com/scholar?q=Ishith+Seth%2C+Bryan+Lim%2C+Yi+Xie%2C+Jevan+Cevik%2C+Warren+M+Rozen%2C+Richard+J+Ross%2C+and+Mathew+Lee%2E+2023%2E+Comparing+the+efficacy+of+large+language+models+Chat%2DGPT%2C+BARD%2C+and+Bing+AI+in+providing+information+)
33. C Shannon, Warren Weaver, and Ch Hockett. 1961. The mathematical theory of communication. Urbana: University of Illinois. [find](https://scholar.google.com/scholar?q=C+Shannon%2C+Warren+Weaver%2C+and+Ch+Hockett%2E+1961%2E+The+mathematical+theory+of+communication%2E+Urbana%3A+University+of+Illinois%2E)
34. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H. Chi, Nathanael Schärli, and Denny Zhou. 2023a. [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 Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine…
35. Jinyang Wu, Feihu Che, Xinxin Zheng, Shuai Zhang, Ruihan Jin, Shuai Nie, Pengpeng Shao, and Jianhua Tao. 2024a. Can large language models understand uncommon meanings of common words? arXiv preprint arXiv:2405.05741. — [arXiv:2405.05741](https://arxiv.org/abs/2405.05741) [find](https://scholar.google.com/scholar?q=Jinyang+Wu%2C+Feihu+Che%2C+Xinxin+Zheng%2C+Shuai+Zhang%2C+Ruihan+Jin%2C+Shuai+Nie%2C+Pengpeng+Shao%2C+and+Jianhua+Tao%2E+2024a%2E+Can+large+language+models+understand+uncommon+meanings+of+common+words%3F+arXiv+preprint+a)
36. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H. Chi, Nathanael Schärli, and Denny Zhou. 2023b. [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 Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine…
37. Jinyang Wu, Feihu Che, Xinxin Zheng, Shuai Zhang, Ruihan Jin, Shuai Nie, Pengpeng Shao, and Jianhua Tao. 2024b. Can large language models understand uncommon meanings of common words? arXiv preprint arXiv:2405.05741. — [arXiv:2405.05741](https://arxiv.org/abs/2405.05741) [find](https://scholar.google.com/scholar?q=Jinyang+Wu%2C+Feihu+Che%2C+Xinxin+Zheng%2C+Shuai+Zhang%2C+Ruihan+Jin%2C+Shuai+Nie%2C+Pengpeng+Shao%2C+and+Jianhua+Tao%2E+2024b%2E+Can+large+language+models+understand+uncommon+meanings+of+common+words%3F+arXiv+preprint+a)
38. Walter W Skeat. 1993. The concise dictionary of English etymology. Wordsworth Editions. [find](https://scholar.google.com/scholar?q=Walter+W+Skeat%2E+1993%2E+The+concise+dictionary+of+English+etymology%2E+Wordsworth+Editions%2E)
39. Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, et al. 2025. Kimi k1. 5: Scaling reinforcement learning with llms. arXiv preprint arXiv:2501.12599. — [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k1-5-scaling-reinforcement/)
40. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
41. Robert Tumarkin and Robert F Whitelaw. 2001. News or noise? internet postings and stock prices. Financial Analysts Journal, 57(3):41–51. [find](https://scholar.google.com/scholar?q=Robert+Tumarkin+and+Robert+F+Whitelaw%2E+2001%2E+News+or+noise%3F+internet+postings+and+stock+prices%2E+Financial+Analysts+Journal%2C+57%283%29%3A41%E2%80%9351%2E)
42. Dilin Wang, Chengyue Gong, and Qiang Liu. 2019. Improving neural language modeling via adversarial training. In International Conference on Machine Learning, pages 6555–6565. PMLR. [find](https://scholar.google.com/scholar?q=Dilin+Wang%2C+Chengyue+Gong%2C+and+Qiang+Liu%2E+2019%2E+Improving+neural+language+modeling+via+adversarial+training%2E+In+International+Conference+on+Machine+Learning%2C+pages+6555%E2%80%936565%2E+PMLR%2E)
43. Wenhui Wang, Hangbo Bao, Shaohan Huang, Li Dong, and Furu Wei. 2021. MiniLMv2: Multi-head self-attention relation distillation for compressing pre-trained transformers. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 2140–2151, Online. Association for Computation… [find](https://scholar.google.com/scholar?q=Wenhui+Wang%2C+Hangbo+Bao%2C+Shaohan+Huang%2C+Li+Dong%2C+and+Furu+Wei%2E+2021%2E+MiniLMv2%3A+Multi%2Dhead+self%2Dattention+relation+distillation+for+compressing+pre%2Dtrained+transformers%2E+In+Findings+of+the+Association+)
44. Yile Wang, Peng Li, Maosong Sun, and Yang Liu. 2023. [Self-knowledge guided retrieval augmentation for large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-self-knowledge-guided-retrieval-augmentation/). In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10303–10315, Singapore. Association for Computational Linguistics.
45. Jinyang Wu, Mingkuan Feng, Shuai Zhang, Ruihan Jin, Feihu Che, Zengqi Wen, and Jianhua Tao. 2025. Boosting multimodal reasoning with mcts-automated structured thinking. arXiv preprint arXiv:2502.02339. — [arXiv:2502.02339](https://arxiv.org/abs/2502.02339) [find](https://scholar.google.com/scholar?q=Jinyang+Wu%2C+Mingkuan+Feng%2C+Shuai+Zhang%2C+Ruihan+Jin%2C+Feihu+Che%2C+Zengqi+Wen%2C+and+Jianhua+Tao%2E+2025%2E+Boosting+multimodal+reasoning+with+mcts%2Dautomated+structured+thinking%2E+arXiv+preprint+arXiv%3A2502%2E02339)
46. Jinyang Wu, Zhiwei Ning, Yidong Ding, Ying Wang, Qinke Peng, and Laiyi Fu. 2023. Kgetcda: an efficient representation learning framework based on knowledge graph encoder from transformer for predicting circrna-disease associations. Briefings in Bioinformatics, 24(5):bbad292. [find](https://scholar.google.com/scholar?q=Jinyang+Wu%2C+Zhiwei+Ning%2C+Yidong+Ding%2C+Ying+Wang%2C+Qinke+Peng%2C+and+Laiyi+Fu%2E+2023%2E+Kgetcda%3A+an+efficient+representation+learning+framework+based+on+knowledge+graph+encoder+from+transformer+for+predictin)
47. Chong Xiang, Tong Wu, Zexuan Zhong, David Wagner, Danqi Chen, and Prateek Mittal. 2024. Certifiably robust RAG against retrieval corruption. In ICML 2024 Next Generation of AI Safety Workshop. [find](https://scholar.google.com/scholar?q=Chong+Xiang%2C+Tong+Wu%2C+Zexuan+Zhong%2C+David+Wagner%2C+Danqi+Chen%2C+and+Prateek+Mittal%2E+2024%2E+Certifiably+robust+RAG+against+retrieval+corruption%2E+In+ICML+2024+Next+Generation+of+AI+Safety+Workshop%2E)
48. Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, and Yu Su. 2024a. [Adaptive chameleon or stubborn sloth: Revealing the behavior of large language models in knowledge conflicts](https://md.research.elamur.ai/free/en/papers/xie-2023-adaptive-chameleon-stubborn-sloth-revealing/). In The Twelfth International Conference on Learning Representations.
49. Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, and Yu Su. 2024b. [Adaptive chameleon or stubborn sloth: Revealing the behavior of large language models in knowledge conflicts](https://md.research.elamur.ai/free/en/papers/xie-2023-adaptive-chameleon-stubborn-sloth-revealing/). In The Twelfth International Conference on Learning Representations.
50. Aiyuan Yang, Bin Xiao, Bingning Wang, Borong Zhang, Ce Bian, Chao Yin, Chenxu Lv, Da Pan, Dian Wang, Dong Yan, et al. 2023. [Baichuan 2: Open large-scale language models](https://md.research.elamur.ai/free/en/papers/yang-2023-baichuan-2-open-large-scale/). arXiv preprint arXiv:2309.10305.
51. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, et al. 2024. Qwen2 technical report. arXiv preprint arXiv:2407.10671. [find](https://scholar.google.com/scholar?q=An+Yang%2C+Baosong+Yang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chang+Zhou%2C+et+al%2E+2024%2E+Qwen2+technical+report%2E+arXiv+preprint+arXiv%3A2407%2E10671%2E)
52. Zihao Wang, Anji Liu, Haowei Lin, Jiaqi Li, Xiaojian Ma, and Yitao Liang. 2024. RAT: Retrieval augmented thoughts elicit context-aware reasoning and verification in long-horizon generation. In NeurIPS 2024 Workshop on Open-World Agents. [find](https://scholar.google.com/scholar?q=Zihao+Wang%2C+Anji+Liu%2C+Haowei+Lin%2C+Jiaqi+Li%2C+Xiaojian+Ma%2C+and+Yitao+Liang%2E+2024%2E+RAT%3A+Retrieval+augmented+thoughts+elicit+context%2Daware+reasoning+and+verification+in+long%2Dhorizon+generation%2E+In+NeurIPS)
53. 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…
54. 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/). Transactions of the Association for Computational Linguistics, 6:287– 302.
55. Junjie Ye, Nuo Xu, Yikun Wang, Jie Zhou, Qi Zhang, Tao Gui, and Xuanjing Huang. 2024. Llm-da: Data augmentation via large language models for few-shot named entity recognition. arXiv preprint arXiv:2402.14568. — [arXiv:2402.14568](https://arxiv.org/abs/2402.14568) [find](https://scholar.google.com/scholar?q=Junjie+Ye%2C+Nuo+Xu%2C+Yikun+Wang%2C+Jie+Zhou%2C+Qi+Zhang%2C+Tao+Gui%2C+and+Xuanjing+Huang%2E+2024%2E+Llm%2Dda%3A+Data+augmentation+via+large+language+models+for+few%2Dshot+named+entity+recognition%2E+arXiv+preprint+arXiv%3A24)
56. Jun Yin, Wen Gao, Jizhizi Li, Pengjian Xu, Chenglin Wu, Borong Lin, and Shuai Lu. 2025. Archidiff: Interactive design of 3d architectural forms generated from a single image. Computers in Industry, 168:104275. by LMSYS, was developed using around 70K user-shared conversations obtained from ShareGPT.… [find](https://scholar.google.com/scholar?q=Jun+Yin%2C+Wen+Gao%2C+Jizhizi+Li%2C+Pengjian+Xu%2C+Chenglin+Wu%2C+Borong+Lin%2C+and+Shuai+Lu%2E+2025%2E+Archidiff%3A+Interactive+design+of+3d+architectural+forms+generated+from+a+single+image%2E+Computers+in+Industry%2C+16)
57. Ori Yoran, Tomer Wolfson, Ori Ram, and Jonathan Berant. 2024. [Making retrieval-augmented language models robust to irrelevant context](https://md.research.elamur.ai/free/en/papers/yoran-2023-making-retrieval-augmented-language-models/). In The Twelfth International Conference on Learning Representations.
58. Qwen2: Proposed by Alibaba Cloud, Qwen series are strong language models, which have been stably pretrained for up to 3 trillion tokens of multilingual data with a wide coverage of domains, languages (with a focus on Chinese and English), etc. Qwen2-7B-Instruct is utilized. [find](https://scholar.google.com/scholar?q=Qwen2%3A+Proposed+by+Alibaba+Cloud%2C+Qwen+series+are+strong+language+models%2C+which+have+been+stably+pretrained+for+up+to+3+trillion+tokens+of+multilingual+data+with+a+wide+coverage+of+domains%2C+languages+)
59. Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, Jie Jiang, and Bin Cui. 2024. [Retrieval-augmented generation for ai-generated content: A survey](https://md.research.elamur.ai/free/en/papers/zhao-2024-retrieval-augmented-generation-ai-generated/). arXiv preprint arXiv:2402.19473.

*Updated 2 November 2026*