{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:57:38Z","timestamp":1774360658693,"version":"3.50.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032212993","type":"print"},{"value":"9783032213006","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-21300-6_26","type":"book-chapter","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:04:44Z","timestamp":1774357484000},"page":"360-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Investigating Retrieval-Augmented Generation Systems on\u00a0Unanswerable, Uncheatable, Realistic, Multi-hop Queries"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0603-1655","authenticated-orcid":false,"given":"Gabrielle Kaili-May","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5779-1662","authenticated-orcid":false,"given":"Bryan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8954-2724","authenticated-orcid":false,"given":"Arman","family":"Cohan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9931-2861","authenticated-orcid":false,"given":"William Gantt","family":"Walden","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-1535","authenticated-orcid":false,"given":"Eugene","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"26_CR1","unstructured":"arxiv. https:\/\/www.arxiv.org\/"},{"key":"26_CR2","unstructured":"biorxiv. https:\/\/biorxiv.org"},{"key":"26_CR3","unstructured":"chemrxiv. https:\/\/www.chemrxiv.org\/"},{"key":"26_CR4","unstructured":"Google news. https:\/\/news.google.com\/"},{"key":"26_CR5","unstructured":"medrxiv. https:\/\/www.medrxiv.org\/"},{"key":"26_CR6","unstructured":"Neuclir corpus. https:\/\/ir-datasets.com\/neuclir.html"},{"key":"26_CR7","unstructured":"Pubmed. https:\/\/pubmed.ncbi.nlm.nih.gov\/"},{"key":"26_CR8","unstructured":"Tokentextsplitter. https:\/\/python.langchain.com\/api_reference\/text_splitters\/base\/langchain_text_splitters.base.TokenTextSplitter.html#tokentextsplitter"},{"key":"26_CR9","unstructured":"Trec 2025 rag corpus. https:\/\/trec-rag.github.io\/annoucements\/2025-rag25-corpus\/"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Agrawal, R., Asrani, M., Youssef, H., Narayan, A.: Scmrag: self-corrective multihop retrieval augmented generation system for LLM agents. In: Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2025, pp. 50\u201358. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC (2025)","DOI":"10.65109\/WJJV5555"},{"key":"26_CR11","doi-asserted-by":"publisher","unstructured":"Asai, A., Min, S., Zhong, Z., Chen, D.: Retrieval-based language models and applications. In: Chen, Y.N.V., Margot, M., Reddy, S. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts), pp. 41\u201346. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-tutorials.6. https:\/\/aclanthology.org\/2023.acl-tutorials.6\/","DOI":"10.18653\/v1\/2023.acl-tutorials.6"},{"key":"26_CR12","unstructured":"Borgeaud, S., et al.: Improving language models by retrieving from trillions of tokens. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 162, pp. 2206\u20132240. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/borgeaud22a.html"},{"key":"26_CR13","unstructured":"Chernogorskii, F., et al.: Dragon: dynamic rag benchmark on news (2025). https:\/\/arxiv.org\/abs\/2507.05713"},{"key":"26_CR14","unstructured":"Friel, R., Belyi, M., Sanyal, A.: Ragbench: explainable benchmark for retrieval-augmented generation systems (2025). https:\/\/arxiv.org\/abs\/2407.11005"},{"key":"26_CR15","doi-asserted-by":"publisher","unstructured":"Gao, T., Yen, H., Yu, J., Chen, D.: Enabling large language models to generate text with citations. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 6465\u20136488. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.398. https:\/\/aclanthology.org\/2023.emnlp-main.398\/","DOI":"10.18653\/v1\/2023.emnlp-main.398"},{"key":"26_CR16","unstructured":"Gonz\u00e1lez Torres, J.J., et al.: Automated question-answer generation for evaluating RAG-based chatbots. In: Demner-Fushman, D., Ananiadou, S., Thompson, P., Ondov, B. (eds.) Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024, pp. 204\u2013214. ELRA and ICCL, Torino, Italia (2024). https:\/\/aclanthology.org\/2024.cl4health-1.25\/"},{"key":"26_CR17","unstructured":"Google: Gemini 2.5 pro model card (2025). https:\/\/modelcards.withgoogle.com\/assets\/documents\/gemini-2.5-pro.pdf"},{"key":"26_CR18","unstructured":"Grattafiori, A., et al.: The llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"26_CR19","doi-asserted-by":"publisher","unstructured":"Ho, X., Duong Nguyen, A.K., Sugawara, S., Aizawa, A.: Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps. In: Scott, D., Bel, N., Zong, C. (eds.) Proceedings of the 28th International Conference on Computational Linguistics, pp. 6609\u20136625. International Committee on Computational Linguistics, Barcelona, Spain (Online) (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.580. https:\/\/aclanthology.org\/2020.coling-main.580\/","DOI":"10.18653\/v1\/2020.coling-main.580"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Cg-rag: research question answering by citation graph retrieval-augmented LLMs (2025). https:\/\/arxiv.org\/abs\/2501.15067","DOI":"10.1145\/3726302.3729920"},{"key":"26_CR21","unstructured":"Lee, J., Kwon, D., Jin, K., Jeong, J., Sim, M., Kim, M.: Mhts: multi-hop tree structure framework for generating difficulty-controllable QA datasets for rag evaluation (2025). https:\/\/arxiv.org\/abs\/2504.08756"},{"key":"26_CR22","doi-asserted-by":"publisher","unstructured":"Lei, D., et al.: FactCG: enhancing fact checkers with graph-based multi-hop data. In: Chiruzzo, L., Ritter, A., Wang, L. (eds.) Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 5002\u20135020. Association for Computational Linguistics, Albuquerque, New Mexico (2025). https:\/\/doi.org\/10.18653\/v1\/2025.naacl-long.258. https:\/\/aclanthology.org\/2025.naacl-long.258\/","DOI":"10.18653\/v1\/2025.naacl-long.258"},{"key":"26_CR23","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9459\u20139474 (2020)"},{"key":"26_CR24","doi-asserted-by":"publisher","unstructured":"Li, Y., Liang, S., Lyu, M., Wang, L.: Making long-context language models better multi-hop reasoners. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2462\u20132475. Association for Computational Linguistics, Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.135. https:\/\/aclanthology.org\/2024.acl-long.135\/","DOI":"10.18653\/v1\/2024.acl-long.135"},{"key":"26_CR25","doi-asserted-by":"publisher","unstructured":"Liu, G.K.M., Shi, B., Caciularu, A., Szpektor, I., Cohan, A.: MDCure: a scalable pipeline for multi-document instruction-following. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 29258\u201329296. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.acl-long.1418. https:\/\/aclanthology.org\/2025.acl-long.1418\/","DOI":"10.18653\/v1\/2025.acl-long.1418"},{"key":"26_CR26","doi-asserted-by":"publisher","unstructured":"Liu, H., et al.: HopRAG: multi-hop reasoning for logic-aware retrieval-augmented generation. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 1897\u20131913. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.97. https:\/\/aclanthology.org\/2025.findings-acl.97\/","DOI":"10.18653\/v1\/2025.findings-acl.97"},{"key":"26_CR27","doi-asserted-by":"publisher","unstructured":"Liu, J.: LlamaIndex (2022). https:\/\/doi.org\/10.5281\/zenodo.1234. https:\/\/github.com\/jerryjliu\/llama_index","DOI":"10.5281\/zenodo.1234"},{"key":"26_CR28","unstructured":"OpenAI: Gpt-5 system card (2025). https:\/\/cdn.openai.com\/gpt-5-system-card.pdf"},{"key":"26_CR29","doi-asserted-by":"publisher","unstructured":"Peng, X., Choubey, P.K., Xiong, C., Wu, C.S.: Unanswerability evaluation for retrieval augmented generation. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8452\u20138472. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.acl-long.415. https:\/\/aclanthology.org\/2025.acl-long.415\/","DOI":"10.18653\/v1\/2025.acl-long.415"},{"key":"26_CR30","doi-asserted-by":"publisher","unstructured":"Peng, Z., Nian, J., Evfimievski, A., Fang, Y.: Eloq: resources for enhancing LLM detection of out-of-scope questions. In: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2025, pp. 3509\u20133519. Association for Computing Machinery, New York, NY, USA (2025). https:\/\/doi.org\/10.1145\/3726302.3730333","DOI":"10.1145\/3726302.3730333"},{"key":"26_CR31","doi-asserted-by":"publisher","unstructured":"Poliakov, M., Shvai, N.: Multi-meta-RAG: improving RAG for multi-hop queries using database filtering with LLM-extracted metadata, pp. 334\u2013342. Springer (2025). https:\/\/doi.org\/10.1007\/978-3-031-81372-6_25","DOI":"10.1007\/978-3-031-81372-6_25"},{"key":"26_CR32","doi-asserted-by":"publisher","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: unanswerable questions for SQuAD. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 784\u2013789. Association for Computational Linguistics, Melbourne, Australia (2018). https:\/\/doi.org\/10.18653\/v1\/P18-2124. https:\/\/aclanthology.org\/P18-2124\/","DOI":"10.18653\/v1\/P18-2124"},{"key":"26_CR33","doi-asserted-by":"publisher","unstructured":"Rosenthal, S., Sil, A., Florian, R., Roukos, S.: CLAPnq: cohesive long-form answers from passages in natural questions for RAG systems. Trans. Assoc. Comput. Linguist. 13, 53\u201372 (2025). https:\/\/doi.org\/10.1162\/tacl_a_00729. https:\/\/aclanthology.org\/2025.tacl-1.3\/","DOI":"10.1162\/tacl_a_00729"},{"key":"26_CR34","unstructured":"Shen, H., et al.: Ragsynth: synthetic data for robust and faithful rag component optimization (2025). https:\/\/arxiv.org\/abs\/2505.10989"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Sun, Y., Yin, Z., Guo, Q., Wu, J., Qiu, X., Zhao, H.: Benchmarking hallucination in large language models based on unanswerable math word problem. In: Calzolari, N., Kan, M.Y., Hoste, V., Lenci, A., Sakti, S., Xue, N. (eds.) Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 2178\u20132188. ELRA and ICCL, Torino, Italia (2024). https:\/\/aclanthology.org\/2024.lrec-main.196\/","DOI":"10.63317\/3jovt56oiu3g"},{"key":"26_CR36","doi-asserted-by":"publisher","unstructured":"Tan, C., et al.: UAQFact: evaluating factual knowledge utilization of LLMs on unanswerable questions. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 1700\u20131715. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.85. https:\/\/aclanthology.org\/2025.findings-acl.85\/","DOI":"10.18653\/v1\/2025.findings-acl.85"},{"key":"26_CR37","unstructured":"Tang, Y., Yang, Y.: Multihop-RAG: benchmarking retrieval-augmented generation for multi-hop queries. In: First Conference on Language Modeling (2024). https:\/\/openreview.net\/forum?id=t4eB3zYWBK"},{"key":"26_CR38","doi-asserted-by":"publisher","unstructured":"Trivedi, H., Balasubramanian, N., Khot, T., Sabharwal, A.: Is multihop QA in DiRe condition? Measuring and reducing disconnected reasoning. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 8846\u20138863. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.712. https:\/\/aclanthology.org\/2020.emnlp-main.712\/","DOI":"10.18653\/v1\/2020.emnlp-main.712"},{"key":"26_CR39","doi-asserted-by":"publisher","unstructured":"Trivedi, H., Balasubramanian, N., Khot, T., Sabharwal, A.: MuSiQue: Multihop questions via single-hop question composition. Trans. Assoc. Comput. Linguist. 10, 539\u2013554 (2022). https:\/\/doi.org\/10.1162\/tacl_a_00475. https:\/\/aclanthology.org\/2022.tacl-1.31\/","DOI":"10.1162\/tacl_a_00475"},{"key":"26_CR40","unstructured":"Yang, X., et al.: Crag - comprehensive rag benchmark. arXiv preprint arXiv:2406.04744 (2024). https:\/\/arxiv.org\/abs\/2406.04744"},{"key":"26_CR41","doi-asserted-by":"publisher","unstructured":"Yang, Z., et al.: HotpotQA: a dataset for diverse, explainable multi-hop question answering. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2369\u20132380. Association for Computational Linguistics, Brussels, Belgium (2018). https:\/\/doi.org\/10.18653\/v1\/D18-1259. https:\/\/aclanthology.org\/D18-1259\/","DOI":"10.18653\/v1\/D18-1259"},{"key":"26_CR42","doi-asserted-by":"publisher","unstructured":"Zhang, J., et al.: LongCite: enabling LLMs to generate fine-grained citations in long-context QA. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Findings of the Association for Computational Linguistics: ACL 2025, pp. 5098\u20135122. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.findings-acl.264. https:\/\/aclanthology.org\/2025.findings-acl.264\/","DOI":"10.18653\/v1\/2025.findings-acl.264"},{"key":"26_CR43","unstructured":"Zhang, Q.W., et al.: Factguard: leveraging multi-agent systems to generate answerable and unanswerable questions for enhanced long-context LLM extraction (2025). https:\/\/arxiv.org\/abs\/2504.05607"},{"key":"26_CR44","doi-asserted-by":"publisher","unstructured":"Zhu, K., et al.: RAGEval: scenario specific RAG evaluation dataset generation framework. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8520\u20138544. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.acl-long.418. https:\/\/aclanthology.org\/2025.acl-long.418\/","DOI":"10.18653\/v1\/2025.acl-long.418"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21300-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:05:00Z","timestamp":1774357500000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21300-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032212993","9783032213006"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21300-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}