Elamur Research⌕
☰
home / papers / 2026 / RBR: RAG-Based Open-Domain Question Answering Using a Ranking Approach to Document Retrieval

RBR: RAG-Based Open-Domain Question Answering Using a Ranking Approach to Document Retrieval

Summary

Open-domain question answering (ODQA) systems based on Retrieval-Augmented Generation (RAG) combine two parts. A retriever selects passages for a query, and a generator writes the answer from them. Standard retrievers score each passage against the query on its own, so they never judge whether one candidate is more useful than another. The authors argue that modelling these relative comparisons between passages can improve retrieval and, in turn, the final answers.

Their system, RBR (Ranking-Based Retrieval), works in two steps:

  • It learns to order candidate passages by relevance to the query.
  • It refines each passage's score with a Graph Attention Network (GAT), which lets candidates inform one another's scores.

The work focuses on the retrieval stage and builds on two baseline systems described in the paper. On Natural Questions and TriviaQA, RBR slightly beats PA-RAG, a recent state-of-the-art ODQA system, in Exact Match. The margins are small, and the authors themselves call the result comparable to the state of the art. The main value of the work is showing that comparative, list-aware relevance modelling is a workable way to strengthen RAG retrievers.

Key points

  • Method: RBR replaces independent query–passage similarity scoring with a ranking step over candidate passages. A GAT (Veličković et al., 2018) then rescores the ranked passages.
  • Evaluation data: Natural Questions (Kwiatkowski et al., 2019) and TriviaQA (Joshi et al., 2017).
  • Results: RBR gains +0.45 Exact Match on Natural Questions and +1.01 Exact Match on TriviaQA over PA-RAG (Wu et al., 2024).
  • Positioning: The paper reviews Naive RAG (DPR retriever with a BART-Large generator), RAG-Fusion, REPLUG, FiD, REAR, REALM and end-to-end retriever training. It presents RBR as an improvement on the retriever side.
  • Publication: Produced at UT Dallas by its Human Language Technology Research Institute; LREC 2026, pages 805–817.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/23z52omk7zss

@inproceedings{naravajhula2026rbr,
  title = {{RBR: RAG-Based Open-Domain Question Answering Using a Ranking Approach to Document Retrieval}},
  author = {Naravajhula, Priyatam Sai and Ng, Vincent},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/23z52omk7zss},
  url = {https://doi.org/10.63317/23z52omk7zss}
}

References

24 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, Arun Rao,… find
  2. Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, and Ming-Wei Chang. 2020. REALM: Retrieval-augmented language model pre-training. In Proceedings of the 37th International Conference on Machine Learning, ICML’20. JMLR.org. find
  3. Gautier Izacard and Edouard Grave. 2021. Leveraging passage retrieval with generative models for open domain question answering. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 874–880, Online. Association for Computa… find our card
  4. Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. 2017. TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611, Vancouver… find our card
  5. 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. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6769–6781, Onli… find our card
  6. Zixuan Ke, Weize Kong, Cheng Li, Mingyang Zhang, Qiaozhu Mei, and Michael Bendersky. 2024. Bridging the preference gap between retrievers and LLMs. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10438–10451, Bangkok, Thailand… find our card
  7. 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… find our card
  8. 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. In Proceedings of the 58th Annual Meeting of th… find our card
  9. 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. In Advances in Neural Information Pro… find
  10. Zackary Rackauckas. 2024. RAG-Fusion: a new take on retrieval-augmented generation. ArXiv:2402.03367 [cs.IR]. — [arXiv:2402.03367](https://arxiv.org/abs/2402.03367) find
  11. Adrian H Rausdashl. 2023. Forget RAG, the Future is RAG-Fusion. Towards Data Sciecne. find
  12. Stephen Robertson, Hugo Zaragoza, et al. 2009. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends® in Information Retrieval, 3(4):333–389. find
  13. Patrick Saint-Dizier. 2013. Advanced question-answering and discourse semantics. In Emerging Applications of Natural Language Processing: Concepts and New Research. IGI Global. find
  14. Kunal Sawarkar, Abhilasha Mangal, and Shivam Raj Solanki. 2024. Blended RAG: Improving RAG (Retriever-Augmented Generation) accuracy with semantic search and hybrid query-based retrievers. In 2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR), volume 24,… find
  15. 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. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Hum… find our card
  16. Robert F. Simmons. 1969. Natural language question-answering systems. Communications of the ACM, 13(1):15–30. find
  17. 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. Transactions of the Association for Computational Linguistics,… find our card
  18. Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, and Suranga Nanayakkara. 2021. Fine-tune the entire RAG architecture (including DPR retriever) for question-answering. ArXiv:2106.11517 [cs.IR]. — [arXiv:2106.11517](https://arxiv.org/abs/2106.11517) find
  19. Karen Sparck Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28(1):11– 21. find
  20. Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations, Vancouver, BC, Canada. find
  21. Yuhao Wang, Ruiyang Ren, Junyi Li, Xin Zhao, Jing Liu, and Ji-Rong Wen. 2024. REAR: A relevance-aware retrieval-augmented framework for open-domain question answering. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5613–5626, Miami, Florida, USA. Ass… find
  22. Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin, and Ming Gao. 2024. PA-RAG: RAG alignment via multi-perspective preference optimization. ArXiv:2412.14510 [cs.CL]. find
  23. Yuhao Zhang, Hongji Zhu, Yongliang Wang, Nan Xu, Xiaobo Li, and Binqiang Zhao. 2022. A contrastive framework for learning sentence representations from pairwise and triple-wise perspective in angular space. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (V… find
  24. Hao Zheng, Zhanlei Yang, Wenju Liu, Jizhong Liang, and Yanpeng Li. 2015. Improving deep neural networks using softplus units. In 2015 International Joint Conference on Neural Networks (IJCNN), pages 1–4. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/naravajhula-2026-rbr-rag-based-open-domain/