IR-RAG @SIGIR25: The Second Edition of the Workshop on Information Retrieval's Role in RAG Systems
Open accessAbstract
In recent years, Retrieval-Augmented Generation (RAG) systems have become a cornerstone of artificial intelligence, attracting considerable attention in a variety of fields. By integrating the strengths of information retrieval and generative models, these systems have shown immense potential to push the boundaries of machine learning applications. Nevertheless, RAG systems still face significant challenges and offer ample room for advancement and innovation.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The concern that gains from stronger retrievers are diminishing or becoming negligible has been raised since 2022 and intensified over time.
“This concern has been raised since 2022, when Gao et al. (2022) asked 'Will a weak retriever theoretically suffice as the NLU and NLG models rapidly become stronger?', and has only intensified over time (Arabzadeh et al., 2025).”
From BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026) · cites this paper as Arabzadeh et al., 2025
The Motivation section (page unavailable) says retrieval has been underexplored despite its crucial role in RAG. The Abstract (page unavailable) likewise calls for studying how improved retrieval can enhance performance. Neither passage addresses whether gains from stronger retrievers are diminishing or whether concern about that possibility has intensified over time; searches for those points found no supporting passage. (LLM, conf=0.76)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 8
- Andrea Bacciu, Florin Cuconasu, Federico Siciliano, Fabrizio Silvestri, Nicola Tonellotto, and Giovanni Trappolini. 2023. RRAML: Reinforced Retrieval Aug- mented Machine Learning. In Proceedings of the Discussion Papers -22nd Interna- tional Conference of the Italian Association for Artificial Intelligence (AIxIA 2023 DP) co-located with 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023), Rome, Italy, November 6-9, 2023 (CEUR Workshop Proceed- ings, Vol. 3537). CEUR-WS.org, 29-37. https://ceur-ws.org/Vol-3537/paper4.pdf
- Andrea Bacciu, Giovanni Trappolini, Andrea Santilli, Emanuele Rodolà, and Fabrizio Silvestri. 2023. Fauno: The Italian Large Language Model that will leave you senza parole!. In Proceedings of the 13th Italian Information Retrieval Workshop (IIR 2023), Pisa, Italy, June 8-9, 2023 (CEUR Workshop Proceedings, Vol. 3448). CEUR- WS.org, 9-17. https://ceur-ws.org/Vol-3448/paper-24.pdf
- Michele Bevilacqua, Giuseppe Ottaviano, Patrick Lewis, Scott Yih, Sebastian Riedel, and Fabio Petroni. 2022. Autoregressive search engines: Generating substrings as document identifiers. Advances in Neural Information Processing Systems 35 (2022), 31668-31683.
- 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. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024). ACM, 719-729. doi:10.1145/3626772.3657834 · DOI · Paper page
- 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. Advances in Neural Information Processing Systems 33 (2020), 9459-9474.
- Fabio Pinelli, Gabriele Tolomei, and Giovanni Trappolini. 2023. FLIRT: Federated Learning for Information Retrieval. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. 3472- 3475.
- Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024). · arXiv
- Giovanni Trappolini, Andrea Santilli, Emanuele Rodolà, Alon Halevy, and Fab- rizio Silvestri. 2023. Multimodal Neural Databases. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (Taipei, Taiwan) (SIGIR '23). Association for Computing Machinery, New York, NY, USA, 2619-2628. doi:10.1145/3539618.3591930 · DOI
Cited by
Sorted by citations
BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents
Chen, Z., Ma, X., Zhuang, S., Nie, P., Zou, K., Sharifymoghaddam, S., Liu, A., Green, J., Patel, K., Meng, R., et al. (2026) · Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2026.acl-long.1023 · Cited by 2 · see citing works
“These benchmarks typically evaluate agents using black-box web search APIs to retrieve supporting documents in real time (Zhou et al., 2025; Chen et al., 2025).”
Self-citation
- Authors
- Arabzadeh, N., Chen, Z., Petroni, F., Siciliano, F., Silvestri, F., & Trappolini, G.
- Affiliations
- University of Waterloo (CA)
- Walmart Global Tech, New York, USA
- Samaya AI, London, United Kingdom
- Sapienza University of Rome (IT)
- ORCID
- Venue
- Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2025-07-13
- Pages
- 4168-4171
- OpenAlex
- W4412378291
- Cited by
- 4
- References
- 0
- Citations by year
- 2026: 3 · 2025: 1
- FWCI
- 4.57
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (publishedVersion, cc-by)
- IRIS Research product catalog (Sapienza University of Rome) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- retrieval-augmented generation, information retrieval, generative models
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
