---
title: "Guaranteeing Knowledge Integration with Joint Decoding for"
description: "The authors propose GuarantRAG, which splits generation into explicit stages instead of making the model reconcile both… 44 references."
authors: ["Zhengyi Zhao", "Shubo Zhang", "Zezhong Wang", "Yuxi Zhang", "Huimin Wang", "Yutian Zhao", "Yefeng Zheng", "Binyang Li", "Kam-Fai Wong", "Xian Wu"]
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.192/"
doi: "10.18653/v1/2026.acl-long.192"
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/zhao-2026-guaranteeing-knowledge-integration-joint-decoding/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhao-2026-guaranteeing-knowledge-integration-joint-decoding/)

[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/35/) / Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation

# Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation

**Authors:** [Zhengyi Zhao](https://md.research.elamur.ai/free/en/authors/zhengyi-zhao/), [Shubo Zhang](https://md.research.elamur.ai/free/en/authors/shubo-zhang/), [Zezhong Wang](https://md.research.elamur.ai/free/en/authors/zezhong-wang/), Yuxi Zhang, Huimin Wang, Yutian Zhao, [Yefeng Zheng](https://md.research.elamur.ai/free/en/authors/yefeng-zheng/), [Binyang Li](https://md.research.elamur.ai/free/en/authors/binyang-li/), [Kam-Fai Wong](https://md.research.elamur.ai/free/en/authors/kam-fai-wong/) and [Xian Wu](https://md.research.elamur.ai/free/en/authors/xian-wu/) · **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.192/) · [PDF](https://aclanthology.org/2026.acl-long.192.pdf) · [DOI 10.18653/v1/2026.acl-long.192](https://doi.org/10.18653/v1/2026.acl-long.192) · [OpenAlex](https://openalex.org/W7166838690)

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

## Summary
Retrieval-augmented generation often fails at integration rather than retrieval. Even with the right documents, an LLM may fall back on its parametric beliefs or splice facts awkwardly into its reasoning. The authors propose GuarantRAG, which splits generation into explicit stages instead of making the model reconcile both knowledge sources in one pass.

A lightweight estimator first decides whether retrieval is needed. The base model then writes an Inner-Answer from memory alone, which serves as a reasoning template. A separately trained Evidence Model produces a Refer-Answer grounded in the retrieved documents. This model is trained with a Contrastive DPO objective: document content is the preferred output, the model's own Inner-Answer is the dispreferred one, and length and query-relevance regularizers are added. At inference, token-level joint decoding follows the Inner-Answer's structure while inserting facts from the most similar Refer-Answer segment.

Across five QA benchmarks, the method beats standard and dynamic RAG baselines. This suggests that how evidence is fused matters as much as what gets retrieved.

## Key points
- In a pilot analysis of 500 knowledge-intensive queries, 67.3% of RAG outputs showed integration failures. These fall into two types: the model ignoring retrieved details, or inserting them in a disjointed way.
- Contrastive DPO uses retrieved documents as "chosen" and the Inner-Answer as "rejected". It is combined with a length penalty (Refer-Answer no longer than Inner-Answer) and a cosine-similarity term between query and answer embeddings.
- The DPO-trained model is not used to produce the final answer directly. Instead, its output is fused with the Inner-Answer through joint decoding, which the authors report works better than naive concatenation.
- Reported gains are up to 12.1% higher accuracy and 16.3% fewer hallucinations. The cost is about 16% more tokens than standard RAG, with the authors reporting lower overhead than SelfRAG and SOLAR. The case study uses Qwen3-14B.
- Full token-level fusion needs hidden-state access. For closed API models, the authors approximate it with prompt-injected instructions and candidate selection by a small local model, which causes some loss in quality and speed.

*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 · 163 works · 21,032 citations
- [Chinese University of Hong Kong](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/) — University, Hong Kong, China · 159 works · 16,154 citations
- [Westlake University](https://md.research.elamur.ai/free/en/universities/westlake-university/) — University, Hangzhou, China · 51 works · 8,572 citations
- [University of International Relations](https://md.research.elamur.ai/free/en/universities/university-of-international-relations/) — University, Beijing, China · 4 works · 1 citation

📚 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): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 552 works

## Cite

Cite as: Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Yuxi Zhang, Huimin Wang, Yutian Zhao, Yefeng Zheng, Binyang Li, Kam-Fai Wong and Xian Wu. 2026. Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation. 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{zhao2026guaranteeing,
  title = {{Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation}},
  author = {Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Yuxi Zhang, Huimin Wang, Yutian Zhao, Yefeng Zheng, Binyang Li, Kam-Fai Wong and Xian Wu},
  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.192},
  url = {https://doi.org/10.18653/v1/2026.acl-long.192}
}
```

- [← previous GSM-Noise: Exploring and Enhancing Large Language Models' Reasoning under Noisy Inputs](https://md.research.elamur.ai/free/en/papers/zhang-2026-gsm-noise-exploring-enhancing-large/)
- [next → GUI0: Self-Evolving Foundational GUI Agents in Super App Ecosystems](https://md.research.elamur.ai/free/en/papers/wang-2026-gui0-self-evolving-foundational-gui/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/35/)

## References

44 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2023. Self-rag: Self-reflective retrieval augmented generation. In NeurIPS 2023 workshop on instruction tuning and instruction following. [find](https://scholar.google.com/scholar?q=Akari+Asai%2C+Zeqiu+Wu%2C+Yizhong+Wang%2C+Avirup+Sil%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+Self%2Drag%3A+Self%2Dreflective+retrieval+augmented+generation%2E+In+NeurIPS+2023+workshop+on+instruction+tuning+and+instruction+)
2. Chi-Min Chan, Chunpu Xu, Ruibin Yuan, Hongyin Luo, Wei Xue, Yike Guo, and Jie Fu. 2024. [Rq-rag: Learning to refine queries for retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/chan-2024-rq-rag-learning-refine-queries/). arXiv preprint arXiv:2404.00610.
3. Shiting Chen, Zijian Zhao, and Jinsong Chen. 2025. Each to their own: Exploring the optimal embedding in rag. arXiv preprint arXiv:2507.17442. — [arXiv:2507.17442](https://arxiv.org/abs/2507.17442) [find](https://scholar.google.com/scholar?q=Shiting+Chen%2C+Zijian+Zhao%2C+and+Jinsong+Chen%2E+2025%2E+Each+to+their+own%3A+Exploring+the+optimal+embedding+in+rag%2E+arXiv+preprint+arXiv%3A2507%2E17442%2E+%E2%80%94+%5BarXiv%3A2507%2E17442%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2507%2E17442%29)
4. Yuyan Chen, Yanghua Xiao, and Bang Liu. 2022. Grow-and-clip: Informative-yet-concise evidence distillation for answer explanation. In 2022 IEEE 38th International Conference on Data Engineering (ICDE), pages 741–754. IEEE. [find](https://scholar.google.com/scholar?q=Yuyan+Chen%2C+Yanghua+Xiao%2C+and+Bang+Liu%2E+2022%2E+Grow%2Dand%2Dclip%3A+Informative%2Dyet%2Dconcise+evidence+distillation+for+answer+explanation%2E+In+2022+IEEE+38th+International+Conference+on+Data+Engineering+%28ICDE%29)
5. Yang Deng, Wenxuan Zhang, Yaliang Li, Min Yang, Wai Lam, and Ying Shen. 2020. Bridging hierarchical and sequential context modeling for question-driven extractive answer summarization. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval,… [find](https://scholar.google.com/scholar?q=Yang+Deng%2C+Wenxuan+Zhang%2C+Yaliang+Li%2C+Min+Yang%2C+Wai+Lam%2C+and+Ying+Shen%2E+2020%2E+Bridging+hierarchical+and+sequential+context+modeling+for+question%2Ddriven+extractive+answer+summarization%2E+In+Proceedings+)
6. Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. [Wizard of wikipedia: Knowledge-powered conversational agents](https://md.research.elamur.ai/free/en/papers/dinan-2018-wizard-wikipedia-knowledge-powered-conversational/). In International Conference on Learning Representations.
7. Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Ji-Rong Wen, and Zhicheng Dou. 2025. Understand what llm needs: Dual preference alignment for retrieval-augmented generation. In Proceedings of the ACM on Web Conference 2025, pages 4206– 4225. [find](https://scholar.google.com/scholar?q=Guanting+Dong%2C+Yutao+Zhu%2C+Chenghao+Zhang%2C+Zechen+Wang%2C+Ji%2DRong+Wen%2C+and+Zhicheng+Dou%2E+2025%2E+Understand+what+llm+needs%3A+Dual+preference+alignment+for+retrieval%2Daugmented+generation%2E+In+Proceedings+of+t)
8. Angela Fan, Yacine Jernite, Ethan Perez, David Grangier, Jason Weston, and Michael Auli. 2019. [Eli5: Long form question answering](https://md.research.elamur.ai/free/en/papers/fan-2019-eli5-long-form-question-answering/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3558–3567.
9. Yixiong Fang, Tianran Sun, Yuling Shi, and Xiaodong Gu. 2025. Attentionrag: Attention-guided context pruning in retrieval-augmented generation. arXiv preprint arXiv:2503.10720. — [arXiv:2503.10720](https://arxiv.org/abs/2503.10720) [find](https://scholar.google.com/scholar?q=Yixiong+Fang%2C+Tianran+Sun%2C+Yuling+Shi%2C+and+Xiaodong+Gu%2E+2025%2E+Attentionrag%3A+Attention%2Dguided+context+pruning+in+retrieval%2Daugmented+generation%2E+arXiv+preprint+arXiv%3A2503%2E10720%2E+%E2%80%94+%5BarXiv%3A2503%2E10720%5D%28ht)
10. Aoran Gan, Hao Yu, Kai Zhang, Qi Liu, Wenyu Yan, Zhenya Huang, Shiwei Tong, and Guoping Hu. 2025. Retrieval augmented generation evaluation in the era of large language models: A comprehensive survey. arXiv preprint arXiv:2504.14891. [find](https://scholar.google.com/scholar?q=Aoran+Gan%2C+Hao+Yu%2C+Kai+Zhang%2C+Qi+Liu%2C+Wenyu+Yan%2C+Zhenya+Huang%2C+Shiwei+Tong%2C+and+Guoping+Hu%2E+2025%2E+Retrieval+augmented+generation+evaluation+in+the+era+of+large+language+models%3A+A+comprehensive+survey%2E)
11. Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2023. [Precise zero-shot dense retrieval without relevance labels](https://md.research.elamur.ai/free/en/papers/gao-2022-precise-zero-shot-dense-retrieval/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1762–1777.
12. Kazuki Hayashi, Hidetaka Kamigaito, Shinya Kouda, and Taro Watanabe. 2025. Iterkey: Iterative keyword generation with llms for enhanced retrieval augmented generation. arXiv preprint arXiv:2505.08450. — [arXiv:2505.08450](https://arxiv.org/abs/2505.08450) [find](https://scholar.google.com/scholar?q=Kazuki+Hayashi%2C+Hidetaka+Kamigaito%2C+Shinya+Kouda%2C+and+Taro+Watanabe%2E+2025%2E+Iterkey%3A+Iterative+keyword+generation+with+llms+for+enhanced+retrieval+augmented+generation%2E+arXiv+preprint+arXiv%3A2505%2E08450%2E)
13. Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, and Jong C. Park. 2024. [Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity](https://md.research.elamur.ai/free/en/papers/jeong-2024-adaptive-rag-learning-adapt-retrieval/). In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics:…
14. Wenqi Jiang, Shuai Zhang, Boran Han, Jie Wang, Bernie Wang, and Tim Kraska. 2024. Piperag: Fast retrieval-augmented generation via algorithm-system co-design. arXiv preprint arXiv:2403.05676. — [arXiv:2403.05676](https://arxiv.org/abs/2403.05676) [find](https://scholar.google.com/scholar?q=Wenqi+Jiang%2C+Shuai+Zhang%2C+Boran+Han%2C+Jie+Wang%2C+Bernie+Wang%2C+and+Tim+Kraska%2E+2024%2E+Piperag%3A+Fast+retrieval%2Daugmented+generation+via+algorithm%2Dsystem+co%2Ddesign%2E+arXiv+preprint+arXiv%3A2403%2E05676%2E+%E2%80%94+%5BarXiv)
15. Zhengbao Jiang, Frank Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023a. [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…
16. Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023b. [Active retrieval augmented generation](https://md.research.elamur.ai/free/en/papers/jiang-2023-active-retrieval-augmented-generation/). In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7969–7992.
17. Rishi Kalra, Zekun Wu, Ayesha Gulley, Airlie Hilliard, Xin Guan, Adriano Koshiyama, and Philip Colin Treleaven. 2024. Hypa-rag: A hybrid parameter adaptive retrieval-augmented generation system for ai legal and policy applications. In Proceedings of the 1st Workshop on Customizable NLP: Progress and… [find](https://scholar.google.com/scholar?q=Rishi+Kalra%2C+Zekun+Wu%2C+Ayesha+Gulley%2C+Airlie+Hilliard%2C+Xin+Guan%2C+Adriano+Koshiyama%2C+and+Philip+Colin+Treleaven%2E+2024%2E+Hypa%2Drag%3A+A+hybrid+parameter+adaptive+retrieval%2Daugmented+generation+system+for+ai)
18. Sanghoon Kim, Dahyun Kim, Chanjun Park, Wonsung Lee, Wonho Song, Yunsu Kim, Hyeonwoo Kim, Yungi Kim, Hyeonju Lee, Jihoo Kim, et al. 2024. Solar 10.7 b: Scaling large language models with simple yet effective depth up-scaling. In Proceedings of the 2024 Conference of the North American Chapter of the… [find](https://scholar.google.com/scholar?q=Sanghoon+Kim%2C+Dahyun+Kim%2C+Chanjun+Park%2C+Wonsung+Lee%2C+Wonho+Song%2C+Yunsu+Kim%2C+Hyeonwoo+Kim%2C+Yungi+Kim%2C+Hyeonju+Lee%2C+Jihoo+Kim%2C+et+al%2E+2024%2E+Solar+10%2E7+b%3A+Scaling+large+language+models+with+simple+yet+ef)
19. 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…
20. Alex Laitenberger, Christopher D. Manning, and Nelson F. Liu. 2025. Stronger baselines for retrieval-augmented generation with long-context language models. arXiv preprint arXiv:2506.03989. [find](https://scholar.google.com/scholar?q=Alex+Laitenberger%2C+Christopher+D%2E+Manning%2C+and+Nelson+F%2E+Liu%2E+2025%2E+Stronger+baselines+for+retrieval%2Daugmented+generation+with+long%2Dcontext+language+models%2E+arXiv+preprint+arXiv%3A2506%2E03989%2E)
21. Carlos Lassance, Hervé Déjean, Thibault Formal, and Stéphane Clinchant. 2024. Splade-v3: New baselines for splade. arXiv preprint arXiv:2403.06789. — [arXiv:2403.06789](https://arxiv.org/abs/2403.06789) [find](https://scholar.google.com/scholar?q=Carlos+Lassance%2C+Herv%C3%A9+D%C3%A9jean%2C+Thibault+Formal%2C+and+St%C3%A9phane+Clinchant%2E+2024%2E+Splade%2Dv3%3A+New+baselines+for+splade%2E+arXiv+preprint+arXiv%3A2403%2E06789%2E+%E2%80%94+%5BarXiv%3A2403%2E06789%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2403%2E0678)
22. Ruizhe Li, Chen Chen, Yuchen Hu, Yanjun Gao, Xi Wang, and Emine Yilmaz. 2025. Attributing response to context: A jensen-shannon divergence driven mechanistic study of context attribution in retrieval-augmented generation. arXiv preprint arXiv:2505.16415. — [arXiv:2505.16415](https://arxiv.org/abs/2505.16415) [find](https://scholar.google.com/scholar?q=Ruizhe+Li%2C+Chen+Chen%2C+Yuchen+Hu%2C+Yanjun+Gao%2C+Xi+Wang%2C+and+Emine+Yilmaz%2E+2025%2E+Attributing+response+to+context%3A+A+jensen%2Dshannon+divergence+driven+mechanistic+study+of+context+attribution+in+retrieval%2D)
23. Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. [Truthfulqa: Measuring how models mimic human falsehoods](https://md.research.elamur.ai/free/en/papers/lin-2022-truthfulqa-measuring-how-models-mimic/). In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3214–3252.
24. Xin Lin, Zhenya Huang, Zhiqiang Zhang, Jun Zhou, and Enhong Chen. 2025. Explore what llm does not know in complex question answering. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 24585–24594. [find](https://scholar.google.com/scholar?q=Xin+Lin%2C+Zhenya+Huang%2C+Zhiqiang+Zhang%2C+Jun+Zhou%2C+and+Enhong+Chen%2E+2025%2E+Explore+what+llm+does+not+know+in+complex+question+answering%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+)
25. Craig Macdonald, Jinyuan Fang, Andrew Parry, and Zaiqiao Meng. 2025. Constructing and evaluating declarative rag pipelines in pyterrier. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 4035–4040. [find](https://scholar.google.com/scholar?q=Craig+Macdonald%2C+Jinyuan+Fang%2C+Andrew+Parry%2C+and+Zaiqiao+Meng%2E+2025%2E+Constructing+and+evaluating+declarative+rag+pipelines+in+pyterrier%2E+In+Proceedings+of+the+48th+International+ACM+SIGIR+Conference+o)
26. Tommy Mordo, Moshe Tennenholtz, and Oren Kurland. 2024. Sponsored question answering. In Proceedings of the 2024 ACM SIGIR International Conference on Theory of Information Retrieval, pages 167– 173. [find](https://scholar.google.com/scholar?q=Tommy+Mordo%2C+Moshe+Tennenholtz%2C+and+Oren+Kurland%2E+2024%2E+Sponsored+question+answering%2E+In+Proceedings+of+the+2024+ACM+SIGIR+International+Conference+on+Theory+of+Information+Retrieval%2C+pages+167%E2%80%93+173%2E)
27. Zackary Rackauckas. 2024. Rag-fusion: a new take on retrieval-augmented generation. International Journal on Natural Language Computing (IJNLC), 13. [find](https://scholar.google.com/scholar?q=Zackary+Rackauckas%2E+2024%2E+Rag%2Dfusion%3A+a+new+take+on+retrieval%2Daugmented+generation%2E+International+Journal+on+Natural+Language+Computing+%28IJNLC%29%2C+13%2E)
28. Zackary Rackauckas, Arthur Câmara, and Jakub Zavrel. 2024. Evaluating rag-fusion with ragelo: an automated elo-based framework. In LLM4Eval@ SIGIR. [find](https://scholar.google.com/scholar?q=Zackary+Rackauckas%2C+Arthur+C%C3%A2mara%2C+and+Jakub+Zavrel%2E+2024%2E+Evaluating+rag%2Dfusion+with+ragelo%3A+an+automated+elo%2Dbased+framework%2E+In+LLM4Eval%40+SIGIR%2E)
29. Mohammad Reza Rezaei and Adji Bousso Dieng. 2025. Vendi-rag: Adaptively trading-off diversity and quality significantly improves retrieval augmented generation with llms. arXiv preprint arXiv:2502.11228. — [arXiv:2502.11228](https://arxiv.org/abs/2502.11228) [find](https://scholar.google.com/scholar?q=Mohammad+Reza+Rezaei+and+Adji+Bousso+Dieng%2E+2025%2E+Vendi%2Drag%3A+Adaptively+trading%2Doff+diversity+and+quality+significantly+improves+retrieval+augmented+generation+with+llms%2E+arXiv+preprint+arXiv%3A2502%2E112)
30. Stephen E Robertson and Steve Walker. 1994. Some simple effective approximations to the 2-poisson model for probabilistic weighted retrieval. In SI-GIR’94: Proceedings of the Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, organised by Dubl… [find](https://scholar.google.com/scholar?q=Stephen+E+Robertson+and+Steve+Walker%2E+1994%2E+Some+simple+effective+approximations+to+the+2%2Dpoisson+model+for+probabilistic+weighted+retrieval%2E+In+SI%2DGIR%E2%80%9994%3A+Proceedings+of+the+Seventeenth+Annual+Intern)
31. Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Tharindu Kaluarachchi, Rajib Rana, and Suranga Nanayakkara. 2023. [Improving the domain adaptation of retrieval augmented generation (rag) models for open domain question answering](https://md.research.elamur.ai/free/en/papers/siriwardhana-2023-improving-domain-adaptation-retrieval-augmented/). Transactions of the Association for Computational Linguistics,…
32. Shangeetha Sivasothy, Scott Barnett, Stefanus Kurniawan, Zafaryab Rasool, and Rajesh Vasa. 2024. Rag-probe: An automated approach for evaluating rag applications. arXiv preprint arXiv:2409.19019. — [arXiv:2409.19019](https://arxiv.org/abs/2409.19019) [find](https://scholar.google.com/scholar?q=Shangeetha+Sivasothy%2C+Scott+Barnett%2C+Stefanus+Kurniawan%2C+Zafaryab+Rasool%2C+and+Rajesh+Vasa%2E+2024%2E+Rag%2Dprobe%3A+An+automated+approach+for+evaluating+rag+applications%2E+arXiv+preprint+arXiv%3A2409%2E19019%2E+%E2%80%94+%5Ba)
33. Weihang Su, Yichen Tang, Qingyao Ai, Zhijing Wu, and Yiqun Liu. 2024. [Dragin: Dynamic retrieval augmented generation based on the real-time information needs of large language models](https://md.research.elamur.ai/free/en/papers/su-2024-dragin-dynamic-retrieval-augmented-generation/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),…
34. Weihang Su, Yichen Tang, Qingyao Ai, Junxi Yan, Changyue Wang, Hongning Wang, Ziyi Ye, Yujia Zhou, and Yiqun Liu. 2025. Parametric retrieval augmented generation. In Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1240–1250. [find](https://scholar.google.com/scholar?q=Weihang+Su%2C+Yichen+Tang%2C+Qingyao+Ai%2C+Junxi+Yan%2C+Changyue+Wang%2C+Hongning+Wang%2C+Ziyi+Ye%2C+Yujia+Zhou%2C+and+Yiqun+Liu%2E+2025%2E+Parametric+retrieval+augmented+generation%2E+In+Proceedings+of+the+48th+Internatio)
35. Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, and William Cohen. 2018. Open domain question answering using early fusion of knowledge bases and text. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4231–4242. [find](https://scholar.google.com/scholar?q=Haitian+Sun%2C+Bhuwan+Dhingra%2C+Manzil+Zaheer%2C+Kathryn+Mazaitis%2C+Ruslan+Salakhutdinov%2C+and+William+Cohen%2E+2018%2E+Open+domain+question+answering+using+early+fusion+of+knowledge+bases+and+text%2E+In+Proceedin)
36. 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/). arXiv preprint arXiv:1803.05355.
37. Yujie Wang, Hu Zhang, Jiye Liang, and Ru Li. 2023. Dynamic heterogeneous-graph reasoning with language models and knowledge representation learning for commonsense question answering. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… [find](https://scholar.google.com/scholar?q=Yujie+Wang%2C+Hu+Zhang%2C+Jiye+Liang%2C+and+Ru+Li%2E+2023%2E+Dynamic+heterogeneous%2Dgraph+reasoning+with+language+models+and+knowledge+representation+learning+for+commonsense+question+answering%2E+In+Proceedings+o)
38. Zilong Wang, Zifeng Wang, Long Le, Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, et al. 2024. Speculative rag: Enhancing retrieval augmented generation through drafting. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Zilong+Wang%2C+Zifeng+Wang%2C+Long+Le%2C+Steven+Zheng%2C+Swaroop+Mishra%2C+Vincent+Perot%2C+Yuwei+Zhang%2C+et+al%2E+2024%2E+Speculative+rag%3A+Enhancing+retrieval+augmented+generation+through+drafting%2E+In+The+Thirteenth+)
39. Di Wu, Wasi Uddin Ahmad, Dejiao Zhang, Murali Krishna Ramanathan, and Xiaofei Ma. 2024. Repoformer: selective retrieval for repository-level code completion. In Proceedings of the 41st International Conference on Machine Learning, pages 53270– 53290. [find](https://scholar.google.com/scholar?q=Di+Wu%2C+Wasi+Uddin+Ahmad%2C+Dejiao+Zhang%2C+Murali+Krishna+Ramanathan%2C+and+Xiaofei+Ma%2E+2024%2E+Repoformer%3A+selective+retrieval+for+repository%2Dlevel+code+completion%2E+In+Proceedings+of+the+41st+International+C)
40. Shitao Xiao, Zheng Liu, Yingxia Shao, and Zhao Cao. 2022. [Retromae: Pre-training retrieval-oriented language models via masked auto-encoder](https://md.research.elamur.ai/free/en/papers/xiao-2022-retromae-pre-training-retrieval-oriented/). In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 538–548.
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.
42. Xiao Yang, Kai Sun, Hao Xin, Yushi Sun, Nikita Bhalla, Xiangsen Chen, Sajal Choudhary, Rongze Gui, Ziran Jiang, Ziyu Jiang, et al. 2024. Crag-comprehensive rag benchmark. Advances in Neural Information Processing Systems, 37:10470–10490. [find](https://scholar.google.com/scholar?q=Xiao+Yang%2C+Kai+Sun%2C+Hao+Xin%2C+Yushi+Sun%2C+Nikita+Bhalla%2C+Xiangsen+Chen%2C+Sajal+Choudhary%2C+Rongze+Gui%2C+Ziran+Jiang%2C+Ziyu+Jiang%2C+et+al%2E+2024%2E+Crag%2Dcomprehensive+rag+benchmark%2E+Advances+in+Neural+Informatio)
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. Shenglai Zeng, Jiankun Zhang, Pengfei He, Yue Xing, Yiding Liu, Han Xu, Jie Ren, Shuaiqiang Wang, Dawei Yin, Yi Chang, et al. 2024. The good and the bad: Exploring privacy issues in retrieval-augmented generation (rag). arXiv preprint arXiv:2402.16893. [find](https://scholar.google.com/scholar?q=Shenglai+Zeng%2C+Jiankun+Zhang%2C+Pengfei+He%2C+Yue+Xing%2C+Yiding+Liu%2C+Han+Xu%2C+Jie+Ren%2C+Shuaiqiang+Wang%2C+Dawei+Yin%2C+Yi+Chang%2C+et+al%2E+2024%2E+The+good+and+the+bad%3A+Exploring+privacy+issues+in+retrieval%2Daugmente)

*Updated 2 November 2026*