---
title: "RAG in the Wild — paper by Xu et al. (2026) — summary and ideas"
description: "The authors test RAG in a mixture-of-knowledge setting using MassiveDS, a 1.4T-token datastore that combines web text… 51 references."
authors: ["Ran Xu", "Yuchen Zhuang", "Yue Yu", "Haoyu Wang", "Wenqi Shi", "Carl Yang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.849/"
doi: "10.18653/v1/2026.findings-acl.849"
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/xu-2026-rag-wild-effectiveness-llms-mixture/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2026-rag-wild-effectiveness-llms-mixture/)

[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/46/) / RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation

# RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation

**Authors:** [Ran Xu](https://md.research.elamur.ai/free/en/authors/ran-xu/), [Yuchen Zhuang](https://md.research.elamur.ai/free/en/authors/yuchen-zhuang/), [Yue Yu](https://md.research.elamur.ai/free/en/authors/yue-yu/), [Haoyu Wang](https://md.research.elamur.ai/free/en/authors/haoyu-wang/), [Wenqi Shi](https://md.research.elamur.ai/free/en/authors/wenqi-shi/) and [Carl Yang](https://md.research.elamur.ai/free/en/authors/carl-yang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/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.findings-acl.849/) · [PDF](https://aclanthology.org/2026.findings-acl.849.pdf) · [DOI 10.18653/v1/2026.findings-acl.849](https://doi.org/10.18653/v1/2026.findings-acl.849) · [OpenAlex](https://openalex.org/W4417268875)

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

## Summary
Most RAG benchmarks are built from Wikipedia or closely related text, so strong results there may say little about deployment against messy, multi-domain collections. The authors test RAG in a mixture-of-knowledge setting using MassiveDS, a 1.4T-token datastore that combines web text (CommonCrawl, C4) with specialised sources such as PubMed, Arxiv, Github and StackExchange. Seven instruct LLMs (Llama, Qwen3 and GPT-4o families) are evaluated on six QA benchmarks covering general, scientific and factual knowledge, with no hint about which source fits each question.

The findings are largely negative:
- Retrieval mainly helps small models. For strong backbones the gains mostly vanish, except on fact-centred questions.
- Adding a reranker barely helps, which points to problems in how retrieved evidence is integrated during generation rather than to weak retrieval alone.
- No single corpus is best across queries.
- LLMs prompted to pick a source route poorly.

The study argues that adaptive, learned source selection is needed before RAG can be trusted on real-world, heterogeneous knowledge.

## Key points
- **Setup:**
  - Benchmarks: MMLU, MMLU-Pro, ARC Challenge, SciQ, CSBench and SimpleQA (Wikipedia-derived items removed).
  - Retrieval: bge-base-en-v1.5 returns the top-5 passages.
  - Reranking: bge-reranker-v2-m3 reorders the top-30 passages before the top-5 are kept.
- **Gains shrink with model scale on MMLU:**
  - Llama-3.2-3B improves by roughly 8–23% depending on domain (e.g., +22.87% in STEM).
  - GPT-4o changes by about ±1%, with small losses in Social Sciences and Humanities.
- **Corpus-specific wins:** for Llama-3.1-8B, about 8%–39% of queries are answered correctly only when retrieving from one particular corpus.
- **Routing fails:** LLM-based source routing underperforms retrieving from all sources and sometimes falls below the no-retrieval baseline. Chain-of-thought adds little, and larger routers do not help.
- **Limitations:** only short-form QA is studied, very large open models are not covered, and latency and efficiency are not measured.

*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

- [Georgia Institute of Technology](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/) — University, Atlanta, United States · 152 works · 27,763 citations
- [Emory University](https://md.research.elamur.ai/free/en/universities/emory-university/) — University, Atlanta, United States · 42 works · 39,899 citations
- [University at Albany, State University of New York](https://md.research.elamur.ai/free/en/universities/university-at-albany-state-university-of-new-york/) — University, Albany, United States · 6 works · 83 citations
- [The University of Texas Southwestern Medical Center](https://md.research.elamur.ai/free/en/hospitals/the-university-of-texas-southwestern-medical-center/) — Hospital, Dallas, United States · 2 works · 649 citations

📚 Shelves (5): [🖥️ 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 · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 552 works

## Cite

Cite as: Ran Xu, Yuchen Zhuang, Yue Yu, Haoyu Wang, Wenqi Shi and Carl Yang. 2026. RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{xu2026rag,
  title = {{RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation}},
  author = {Ran Xu, Yuchen Zhuang, Yue Yu, Haoyu Wang, Wenqi Shi and Carl Yang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.849},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.849}
}
```

- [← previous RAG as a collapsed NLG pipeline](https://md.research.elamur.ai/free/en/papers/sivaprasad-2026-rag-as-collapsed-nlg-pipeline/)
- [next → RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World](https://md.research.elamur.ai/free/en/papers/liu-2026-rag-or-learning-understanding-limits/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/46/)

## References

51 references, 30 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Our study primarily targets question answering tasks with short-form answers, which may limit the applicability of our results to other settings such as open-ended generation or long-form reasoning. While we evaluate several widely used models, our experiments do not comprehensively cover larger ope… — [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/)
2. Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. [Bge m3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation](https://md.research.elamur.ai/free/en/papers/chen-2024-m3-embedding-multi-linguality/). arXiv preprint arXiv:2402.03216.
3. Zhe Chen, Yusheng Liao, Shuyang Jiang, Pingjie Wang, Yiqiu Guo, Yanfeng Wang, and Yu Wang. 2025. Towards omni-rag: Comprehensive retrieval-augmented generation for large language models in medical applications. arXiv preprint arXiv:2501.02460. [find](https://scholar.google.com/scholar?q=Zhe+Chen%2C+Yusheng+Liao%2C+Shuyang+Jiang%2C+Pingjie+Wang%2C+Yiqiu+Guo%2C+Yanfeng+Wang%2C+and+Yu+Wang%2E+2025%2E+Towards+omni%2Drag%3A+Comprehensive+retrieval%2Daugmented+generation+for+large+language+models+in+medical+app)
4. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. [Think you have solved question answering? try arc, the ai2 reasoning challenge](https://md.research.elamur.ai/free/en/papers/clark-2018-think-have-solved-question-answering/). arXiv preprint arXiv:1803.05457.
5. Florin Cuconasu, Giovanni Trappolini, Federico Siciliano, Simone Filice, Cesare Campagnano, Yoelle Maarek, Nicola Tonellotto, and Fabrizio Silvestri. 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 Developm…
6. Evan Frick, Connor Chen, Joseph Tennyson, Tianle Li, Wei-Lin Chiang, Anastasios N Angelopoulos, and Ion Stoica. 2025. Prompt-to-leaderboard. arXiv preprint arXiv:2502.14855. [find](https://scholar.google.com/scholar?q=Evan+Frick%2C+Connor+Chen%2C+Joseph+Tennyson%2C+Tianle+Li%2C+Wei%2DLin+Chiang%2C+Anastasios+N+Angelopoulos%2C+and+Ion+Stoica%2E+2025%2E+Prompt%2Dto%2Dleaderboard%2E+arXiv+preprint+arXiv%3A2502%2E14855%2E)
7. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, et al. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783.
8. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). In International Conference on Learning Representations.
9. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, Kristina Toutanova, Llion Jones, Matthew Kelcey, Ming-Wei Chang, Andrew M. Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. [Natural…](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/)
10. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 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, 33:9459–9474.
11. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/). arXiv preprint arXiv:2501.05366.
12. Jie Huang, Wei Ping, Peng Xu, Mohammad Shoeybi, Kevin Chang, and Bryan Catanzaro. 2024. RAVEN: In-context learning with retrieval-augmented encoder-decoder language models. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Jie+Huang%2C+Wei+Ping%2C+Peng+Xu%2C+Mohammad+Shoeybi%2C+Kevin+Chang%2C+and+Bryan+Catanzaro%2E+2024%2E+RAVEN%3A+In%2Dcontext+learning+with+retrieval%2Daugmented+encoder%2Ddecoder+language+models%2E+In+First+Conference+on+Lang)
13. Xi Victoria Lin, Xilun Chen, Mingda Chen, Weijia Shi, Maria Lomeli, Richard James, Pedro Rodriguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, Luke Zettlemoyer, and Wen tau Yih. 2024. [RA-DIT: Retrieval-augmented dual instruction tuning](https://md.research.elamur.ai/free/en/papers/lin-2023-ra-dit-retrieval-augmented-dual/). In The Twelfth International Conference on Learning Representati…
14. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276.
15. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+et+al%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+arXiv+preprint+arXiv%3A2412%2E19437%2E)
16. Shayekh Bin Islam, Md Asib Rahman, K S M Tozammel Hossain, Enamul Hoque, Shafiq Joty, and Md Rizwan Parvez. 2024. Open-RAG: Enhanced retrieval augmented reasoning with open-source large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14231– 14244, Mia… [find](https://scholar.google.com/scholar?q=Shayekh+Bin+Islam%2C+Md+Asib+Rahman%2C+K+S+M+Tozammel+Hossain%2C+Enamul+Hoque%2C+Shafiq+Joty%2C+and+Md+Rizwan+Parvez%2E+2024%2E+Open%2DRAG%3A+Enhanced+retrieval+augmented+reasoning+with+open%2Dsource+large+language+model)
17. Xinbei Ma, Yeyun Gong, Pengcheng He, hai zhao, and Nan Duan. 2023. [Query rewriting in retrieval-augmented large language models](https://md.research.elamur.ai/free/en/papers/ma-2023-query-rewriting-retrieval-augmented-large/). In The 2023 Conference on Empirical Methods in Natural Language Processing.
18. Gautier Izacard, Patrick 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/). Journal of Machine Learning Research, 24(251):1–43.
19. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. [Search-r1: Training llms to reason and leverage search engines with reinforcement learning](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/). arXiv preprint arXiv:2503.09516.
20. Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. 2017. [TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611, Vancouver…
21. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2023. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (V… [find](https://scholar.google.com/scholar?q=Alex+Mallen%2C+Akari+Asai%2C+Victor+Zhong%2C+Rajarshi+Das%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+When+not+to+trust+language+models%3A+Investigating+effectiveness+of+parametric+and+non%2Dparametric+mem)
22. AI Meta. 2025. The llama 4 herd: The beginning of a new era of natively multimodal ai innovation. [find](https://scholar.google.com/scholar?q=AI+Meta%2E+2025%2E+The+llama+4+herd%3A+The+beginning+of+a+new+era+of+natively+multimodal+ai+innovation%2E)
23. Feiteng Mu, Yong Jiang, Liwen Zhang, Liuchu Liuchu, Wenjie Li, Pengjun Xie, and Fei Huang. 2024. Query routing for homogeneous tools: An instantiation in the RAG scenario. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10225–10230, Miami, Florida, USA. Association fo… [find](https://scholar.google.com/scholar?q=Feiteng+Mu%2C+Yong+Jiang%2C+Liwen+Zhang%2C+Liuchu+Liuchu%2C+Wenjie+Li%2C+Pengjun+Xie%2C+and+Fei+Huang%2E+2024%2E+Query+routing+for+homogeneous+tools%3A+An+instantiation+in+the+RAG+scenario%2E+In+Findings+of+the+Associati)
24. Feiteng Mu, Liwen Zhang, Yong Jiang, Wenjie Li, Zhen Zhang, Pengjun Xie, and Fei Huang. 2025. Unsupervised query routing for retrieval augmented generation. arXiv preprint arXiv:2501.07793. — [arXiv:2501.07793](https://arxiv.org/abs/2501.07793) [find](https://scholar.google.com/scholar?q=Feiteng+Mu%2C+Liwen+Zhang%2C+Yong+Jiang%2C+Wenjie+Li%2C+Zhen+Zhang%2C+Pengjun+Xie%2C+and+Fei+Huang%2E+2025%2E+Unsupervised+query+routing+for+retrieval+augmented+generation%2E+arXiv+preprint+arXiv%3A2501%2E07793%2E+%E2%80%94+%5BarXiv%3A2)
25. Cheng Niu, Yuanhao Wu, Juno Zhu, Siliang Xu, KaShun Shum, Randy Zhong, Juntong Song, and Tong Zhang. 2024. [RAGTruth: A hallucination corpus for developing trustworthy retrieval-augmented language models](https://md.research.elamur.ai/free/en/papers/niu-2024-ragtruth-hallucination-corpus-developing-trustworthy/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volu…
26. Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E. Gonzalez, M Waleed Kadous, and Ion Stoica. 2025. RouteLLM: Learning to route LLMs from preference data. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Isaac+Ong%2C+Amjad+Almahairi%2C+Vincent+Wu%2C+Wei%2DLin+Chiang%2C+Tianhao+Wu%2C+Joseph+E%2E+Gonzalez%2C+M+Waleed+Kadous%2C+and+Ion+Stoica%2E+2025%2E+RouteLLM%3A+Learning+to+route+LLMs+from+preference+data%2E+In+The+Thirteenth+)
27. Fabio Petroni, Aleksandra Piktus, Angela Fan, Patrick Lewis, Majid Yazdani, Nicola De Cao, James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, Vassilis Plachouras, Tim Rocktäschel, and Sebastian Riedel. 2021. [KILT: a benchmark for knowledge intensive language tasks](https://md.research.elamur.ai/free/en/papers/petroni-2020-kilt-benchmark-knowledge-intensive-language/). In Proceedings of th…
28. Rulin Shao, Jacqueline He, Akari Asai, Weijia Shi, Tim Dettmers, Sewon Min, Luke Zettlemoyer, and Pang Wei W Koh. 2024. Scaling retrieval-based language models with a trillion-token datastore. Advances in Neural Information Processing Systems, 37:91260– 91299. [find](https://scholar.google.com/scholar?q=Rulin+Shao%2C+Jacqueline+He%2C+Akari+Asai%2C+Weijia+Shi%2C+Tim+Dettmers%2C+Sewon+Min%2C+Luke+Zettlemoyer%2C+and+Pang+Wei+W+Koh%2E+2024%2E+Scaling+retrieval%2Dbased+language+models+with+a+trillion%2Dtoken+datastore%2E+Advance)
29. Rulin Shao, Rui Qiao, Varsha Kishore, Niklas Muennighoff, Xi Victoria Lin, Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Wen-tau Yih, Pang Wei Koh, et al. 2025. Reasonir: Training retrievers for reasoning tasks. arXiv preprint arXiv:2504.20595. [find](https://scholar.google.com/scholar?q=Rulin+Shao%2C+Rui+Qiao%2C+Varsha+Kishore%2C+Niklas+Muennighoff%2C+Xi+Victoria+Lin%2C+Daniela+Rus%2C+Bryan+Kian+Hsiang+Low%2C+Sewon+Min%2C+Wen%2Dtau+Yih%2C+Pang+Wei+Koh%2C+et+al%2E+2025%2E+Reasonir%3A+Training+retrievers+for+reas)
30. 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…
31. Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Richard James, Mike Lewis, Luke Zettlemoyer, and Wen-tau Yih. 2024. [REPLUG: Retrieval-augmented black-box language models](https://md.research.elamur.ai/free/en/papers/shi-2023-replug-retrieval-augmented-black-box/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Hum…
32. Xiaoshuai Song, Muxi Diao, Guanting Dong, Zhengyang Wang, Yujia Fu, Runqi Qiao, Zhexu Wang, Dayuan Fu, Huangxuan Wu, Bin Liang, Weihao Zeng, Yejie Wang, Zhuoma GongQue, Jianing Yu, Qiuna Tan, and Weiran Xu. 2025. CS-bench: A comprehensive benchmark for large language models towards computer science… [find](https://scholar.google.com/scholar?q=Xiaoshuai+Song%2C+Muxi+Diao%2C+Guanting+Dong%2C+Zhengyang+Wang%2C+Yujia+Fu%2C+Runqi+Qiao%2C+Zhexu+Wang%2C+Dayuan+Fu%2C+Huangxuan+Wu%2C+Bin+Liang%2C+Weihao+Zeng%2C+Yejie+Wang%2C+Zhuoma+GongQue%2C+Jianing+Yu%2C+Qiuna+Tan%2C+and+Weir)
33. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. [FEVER: a large-scale dataset for fact extraction and VERification](https://md.research.elamur.ai/free/en/papers/thorne-2018-fever-large-scale-dataset-fact/). In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vo…
34. 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…
35. Haoyu Wang, Ruirui Li, Haoming Jiang, Jinjin Tian, Zhengyang Wang, Chen Luo, Xianfeng Tang, Monica Xiao Cheng, Tuo Zhao, and Jing Gao. 2024a. BlendFilter: Advancing retrieval-augmented large language models via query generation blending and knowledge filtering. In Proceedings of the 2024 Conference… [find](https://scholar.google.com/scholar?q=Haoyu+Wang%2C+Ruirui+Li%2C+Haoming+Jiang%2C+Jinjin+Tian%2C+Zhengyang+Wang%2C+Chen+Luo%2C+Xianfeng+Tang%2C+Monica+Xiao+Cheng%2C+Tuo+Zhao%2C+and+Jing+Gao%2E+2024a%2E+BlendFilter%3A+Advancing+retrieval%2Daugmented+large+language+)
36. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, Tianle Li, Max Ku, Kai Wang, Alex Zhuang, Rongqi Fan, Xiang Yue, and Wenhu Chen. 2024b. [MMLU-pro: A more robust and challenging multi-task language understanding benchmar…](https://md.research.elamur.ai/free/en/papers/wang-2024-mmlu-pro-more-robust-challenging/)
37. Jason Wei, Nguyen Karina, Hyung Won Chung, Yunxin Joy Jiao, Spencer Papay, Amelia Glaese, John Schulman, and William Fedus. 2024. [Measuring short-form factuality in large language models](https://md.research.elamur.ai/free/en/papers/wei-2024-measuring-short-form-factuality-large/). arXiv preprint arXiv:2411.04368.
38. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 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/). Advances in neural information processing systems, 35:24824–24837.
39. Johannes Welbl, Nelson F Liu, and Matt Gardner. 2017. [Crowdsourcing multiple choice science questions](https://md.research.elamur.ai/free/en/papers/welbl-2017-crowdsourcing-multiple-choice-science-questions/). arXiv preprint arXiv:1707.06209.
40. Di Wu, Jia-Chen Gu, Kai-Wei Chang, and Nanyun Peng. 2025. Self-routing rag: Binding selective retrieval with knowledge verbalization. arXiv preprint arXiv:2504.01018. — [arXiv:2504.01018](https://arxiv.org/abs/2504.01018) [find](https://scholar.google.com/scholar?q=Di+Wu%2C+Jia%2DChen+Gu%2C+Kai%2DWei+Chang%2C+and+Nanyun+Peng%2E+2025%2E+Self%2Drouting+rag%3A+Binding+selective+retrieval+with+knowledge+verbalization%2E+arXiv+preprint+arXiv%3A2504%2E01018%2E+%E2%80%94+%5BarXiv%3A2504%2E01018%5D%28https%3A%2F%2Farxi)
41. Guangzhi Xiong, Qiao Jin, Zhiyong Lu, and Aidong Zhang. 2024. [Benchmarking retrieval-augmented generation for medicine](https://md.research.elamur.ai/free/en/papers/xiong-2024-benchmarking-retrieval-augmented-generation-medicine/). In Findings of the Association for Computational Linguistics: ACL 2024, pages 6233–6251, Bangkok, Thailand. Association for Computational Linguistics.
42. Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Bowen Jin, May Dongmei Wang, Joyce Ho, and Carl Yang. 2024a. RAM-EHR: Retrieval augmentation meets clinical predictions on electronic health records. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short… [find](https://scholar.google.com/scholar?q=Ran+Xu%2C+Wenqi+Shi%2C+Yue+Yu%2C+Yuchen+Zhuang%2C+Bowen+Jin%2C+May+Dongmei+Wang%2C+Joyce+Ho%2C+and+Carl+Yang%2E+2024a%2E+RAM%2DEHR%3A+Retrieval+augmentation+meets+clinical+predictions+on+electronic+health+records%2E+In+Proce)
43. Tianjun Zhang, Shishir G Patil, Naman Jain, Sheng Shen, Matei Zaharia, Ion Stoica, and Joseph E. Gonzalez. 2024. [RAFT: Adapting language model to domain specific RAG](https://md.research.elamur.ai/free/en/papers/zhang-2024-raft-adapting-language-model-domain/). In First Conference on Language Modeling.
44. Shengyao Zhuang, Xueguang Ma, Bevan Koopman, Jimmy Lin, and Guido Zuccon. 2025. Rank-r1: Enhancing reasoning in llm-based document rerankers via reinforcement learning. arXiv preprint arXiv:2503.06034. — [arXiv:2503.06034](https://arxiv.org/abs/2503.06034) [find](https://scholar.google.com/scholar?q=Shengyao+Zhuang%2C+Xueguang+Ma%2C+Bevan+Koopman%2C+Jimmy+Lin%2C+and+Guido+Zuccon%2E+2025%2E+Rank%2Dr1%3A+Enhancing+reasoning+in+llm%2Dbased+document+rerankers+via+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2503%2E06034)
45. Ran Xu, Wenqi Shi, Yue Yu, Yuchen Zhuang, Yanqiao Zhu, May Dongmei Wang, Joyce C. Ho, Chao Zhang, and Carl Yang. 2024b. Bmretriever: Tuning large language models as better biomedical text retrievers. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 222… [find](https://scholar.google.com/scholar?q=Ran+Xu%2C+Wenqi+Shi%2C+Yue+Yu%2C+Yuchen+Zhuang%2C+Yanqiao+Zhu%2C+May+Dongmei+Wang%2C+Joyce+C%2E+Ho%2C+Chao+Zhang%2C+and+Carl+Yang%2E+2024b%2E+Bmretriever%3A+Tuning+large+language+models+as+better+biomedical+text+retrievers%2E+)
46. Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, and Jie Zhou. 2024c. Unsupervised information refinement training of large language models for retrieval-augmented generation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1:… [find](https://scholar.google.com/scholar?q=Shicheng+Xu%2C+Liang+Pang%2C+Mo+Yu%2C+Fandong+Meng%2C+Huawei+Shen%2C+Xueqi+Cheng%2C+and+Jie+Zhou%2E+2024c%2E+Unsupervised+information+refinement+training+of+large+language+models+for+retrieval%2Daugmented+generation%2E+I)
47. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
48. 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…
49. Zijun Yao, Weijian Qi, Liangming Pan, Shulin Cao, Linmei Hu, Weichuan Liu, Lei Hou, and Juanzi Li. 2024. [Seakr: Self-aware knowledge retrieval for adaptive retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/yao-2025-seakr-self-aware-knowledge-retrieval/). arXiv preprint arXiv:2406.19215.
50. Yue Yu, Wei Ping, Zihan Liu, Boxin Wang, Jiaxuan You, Chao Zhang, Mohammad Shoeybi, and Bryan Catanzaro. 2024. RankRAG: Unifying context ranking with retrieval-augmented generation in LLMs. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Yue+Yu%2C+Wei+Ping%2C+Zihan+Liu%2C+Boxin+Wang%2C+Jiaxuan+You%2C+Chao+Zhang%2C+Mohammad+Shoeybi%2C+and+Bryan+Catanzaro%2E+2024%2E+RankRAG%3A+Unifying+context+ranking+with+retrieval%2Daugmented+generation+in+LLMs%2E+In+The+Thi)
51. Jiarui Zhang, Xiangyu Liu, Yong Hu, Chaoyue Niu, Fan Wu, and Guihai Chen. 2025. Query routing for retrieval-augmented language models. arXiv preprint arXiv:2505.23052. — [arXiv:2505.23052](https://arxiv.org/abs/2505.23052) [find](https://scholar.google.com/scholar?q=Jiarui+Zhang%2C+Xiangyu+Liu%2C+Yong+Hu%2C+Chaoyue+Niu%2C+Fan+Wu%2C+and+Guihai+Chen%2E+2025%2E+Query+routing+for+retrieval%2Daugmented+language+models%2E+arXiv+preprint+arXiv%3A2505%2E23052%2E+%E2%80%94+%5BarXiv%3A2505%2E23052%5D%28https%3A%2F%2Farx)

*Updated 2 November 2026*