{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T19:17:04Z","timestamp":1787858224198,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":36,"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_45","type":"book-chapter","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:04:25Z","timestamp":1774357465000},"page":"537-546","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Principled Context Engineering for\u00a0RAG: Statistical Guarantees via\u00a0Conformal Prediction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8656-9406","authenticated-orcid":false,"given":"Debashish","family":"Chakraborty","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0051-1535","authenticated-orcid":false,"given":"Eugene","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7664-2230","authenticated-orcid":false,"given":"Daniel","family":"Khashabi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7347-7086","authenticated-orcid":false,"given":"Dawn","family":"Lawrie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8107-4383","authenticated-orcid":false,"given":"Kevin","family":"Duh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"45_CR1","unstructured":"Vector Indexing | Weaviate Documentation \u2014 docs.weaviate.io. https:\/\/docs.weaviate.io\/weaviate\/concepts\/vector-index. Accessed 24 Sept 2025"},{"key":"45_CR2","unstructured":"Angelopoulos, A.N., Bates, S.: A gentle introduction to conformal prediction and distribution-free uncertainty quantification. ArXiv abs\/2107.07511 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235899036"},{"key":"45_CR3","doi-asserted-by":"publisher","unstructured":"Asgari, E., Monta\u00f1a-Brown, N., Dubois, M., Khalil, S., Balloch, J., Pimenta, D.: A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation. medRxiv (2024). https:\/\/doi.org\/10.1101\/2024.09.12.24313556, https:\/\/www.medrxiv.org\/content\/early\/2024\/09\/13\/2024.09.12.24313556","DOI":"10.1101\/2024.09.12.24313556"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Br\u00e5dland, H., Olsen, M.G., Andersen, P.A., Nossum, A.S., Gupta, A.: A new hope: Domain-agnostic automatic evaluation of text chunking. ArXiv:abs\/2505.02171 (2025). https:\/\/api.semanticscholar.org\/CorpusID:278327433","DOI":"10.1145\/3726302.3729882"},{"key":"45_CR5","unstructured":"Dubey, A., et al.: The llama 3 herd of models. ArXiv:abs\/2407.21783 (2024). https:\/\/api.semanticscholar.org\/CorpusID:271571434"},{"key":"45_CR6","doi-asserted-by":"crossref","unstructured":"Feng, N., Sui, Y., Hou, S., Cresswell, J.C., Wu, G.: Response quality assessment for retrieval-augmented generation via conditional conformal factuality. ArXiv:abs\/2506.20978 (2025). https:\/\/api.semanticscholar.org\/CorpusID:280011519","DOI":"10.1145\/3726302.3730244"},{"key":"45_CR7","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. ArXiv:abs\/1706.04599 (2017). https:\/\/api.semanticscholar.org\/CorpusID:28671436"},{"key":"45_CR8","unstructured":"Hong, K., Troynikov, A., Huber, J.: Context rot: How increasing input tokens impacts LLM performance. Tech. rep., Chroma (July 2025). https:\/\/research.trychroma.com\/context-rot"},{"key":"45_CR9","unstructured":"Hsieh, C.P., et al.: Ruler: What\u2019s the real context size of your long-context language models? ArXiv:abs\/2404.06654 (2024)"},{"key":"45_CR10","unstructured":"Hurst, O.A., et al.: Gpt-4o system card. ArXiv:abs\/2410.21276 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273662196"},{"key":"45_CR11","unstructured":"Kang, M., Gurel, N.M., Yu, N., Song, D.X., Li, B.: C-rag: Certified generation risks for retrieval-augmented language models. ArXiv:abs\/2402.03181 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267412330"},{"key":"45_CR12","unstructured":"Lawrie, D., MacAvaney, S., Mayfield, J., Soldaini, L., Yang, E., Yates, A.: TREC RAGTIME: RAG TREC Instrument for Multilingual Evaluation. https:\/\/trec-ragtime.github.io (2025), official website for the TREC RAGTIME track"},{"key":"45_CR13","unstructured":"Lawrie, D.J., et al.: Overview of the trec 2024 neuclir track (2025). https:\/\/api.semanticscholar.org\/CorpusID:281394231"},{"key":"45_CR14","doi-asserted-by":"crossref","unstructured":"Lei, J., G\u2019Sell, M.G., Rinaldo, A., Tibshirani, R.J., Wasserman, L.A.: Distribution-free predictive inference for regression. J. Am. Stat. Assoc. 113, 1094 \u2013 1111 (2016). https:\/\/api.semanticscholar.org\/CorpusID:13741419","DOI":"10.1080\/01621459.2017.1307116"},{"key":"45_CR15","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks (2021). https:\/\/arxiv.org\/abs\/2005.11401"},{"key":"45_CR16","doi-asserted-by":"publisher","unstructured":"Li, S., Park, S., Lee, I., Bastani, O.: TRAQ: Trustworthy retrieval augmented question answering via conformal prediction. In: Duh, K., Gomez, H., Bethard, S. (eds.) Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 3799\u20133821. Association for Computational Linguistics, Mexico City, Mexico (Jun 2024). https:\/\/doi.org\/10.18653\/v1\/2024.naacl-long.210, https:\/\/aclanthology.org\/2024.naacl-long.210\/","DOI":"10.18653\/v1\/2024.naacl-long.210"},{"key":"45_CR17","doi-asserted-by":"publisher","unstructured":"Li, X., Zhu, C., Li, L., Yin, Z., Sun, T., Qiu, X.: LLatrieval: LLM-verified retrieval for verifiable generation. In: Duh, K., Gomez, H., Bethard, S. (eds.) Proceedings of the 2024 Conference of he North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 5453\u20135471. Association for Computational Linguistics, Mexico City, Mexico (Jun 2024). https:\/\/doi.org\/10.18653\/v1\/2024.naacl-long.305, https:\/\/aclanthology.org\/2024.naacl-long.305\/","DOI":"10.18653\/v1\/2024.naacl-long.305"},{"key":"45_CR18","doi-asserted-by":"publisher","unstructured":"Liu, N.F., et al.: Lost in the middle: How language models use long contexts. Trans. Assoc. Comput. Linguist. 12, 157\u2013173 (2024). https:\/\/doi.org\/10.1162\/tacl_a_00638, https:\/\/aclanthology.org\/2024.tacl-1.9\/","DOI":"10.1162\/tacl_a_00638"},{"key":"45_CR19","unstructured":"LlamaIndex Developers: Llamaindex python framework: Embeddings module guide. https:\/\/developers.llamaindex.ai\/python\/framework\/module_guides\/models\/embeddings\/ (2025). Accessed Oct 2025"},{"key":"45_CR20","unstructured":"Lovering, C., et al.: Language model probabilities are not calibrated in numeric contexts (2024). https:\/\/api.semanticscholar.org\/CorpusID:273502432"},{"key":"45_CR21","unstructured":"Magesh, V., Surani, F., Dahl, M., Suzgun, M., Manning, C.D., Ho, D.E.: Hallucination-free? assessing the reliability of leading ai legal research tools. ArXiv:abs\/2405.20362 (2024). https:\/\/api.semanticscholar.org\/CorpusID:269976547"},{"key":"45_CR22","doi-asserted-by":"publisher","unstructured":"Mayfield, J., et al.: On the evaluation of machine-generated reports. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1904\u20131915. SIGIR \u201924, Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3626772.3657846","DOI":"10.1145\/3626772.3657846"},{"key":"45_CR23","doi-asserted-by":"publisher","unstructured":"Niu, C., et al.: RAGTruth: A hallucination corpus for developing trustworthy retrieval-augmented language models. 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. 10862\u201310878. Association for Computational Linguistics, Bangkok, Thailand (Aug 2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.585, https:\/\/aclanthology.org\/2024.acl-long.585\/","DOI":"10.18653\/v1\/2024.acl-long.585"},{"key":"45_CR24","unstructured":"Rajasekaran, P., et al.: Effective context engineering for ai agents. https:\/\/www.anthropic.com\/engineering\/effective-context-engineering-for-ai-agents (2025), anthropic Engineering Blog, Published September 29, 2025"},{"key":"45_CR25","unstructured":"Rouzrokh, P., Faghani, S., Gamble, C., Shariatnia, M., Erickson, B.J.: Conflare: Conformal large language model retrieval. ArXiv:abs\/2404.04287 (2024). https:\/\/api.semanticscholar.org\/CorpusID:269004787"},{"key":"45_CR26","doi-asserted-by":"publisher","unstructured":"Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 3784\u20133803. Association for Computational Linguistics, Punta Cana, Dominican Republic (Nov 2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.320, https:\/\/aclanthology.org\/2021.findings-emnlp.320\/","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"45_CR27","doi-asserted-by":"publisher","unstructured":"Slobodkin, A., Hirsch, E., Cattan, A., Schuster, T., Dagan, I.: Attribute first, then generate: Locally-attributable grounded text generation. 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. 3309\u20133344. Association for Computational Linguistics, Bangkok, Thailand (Aug 2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.182, https:\/\/aclanthology.org\/2024.acl-long.182\/","DOI":"10.18653\/v1\/2024.acl-long.182"},{"key":"45_CR28","unstructured":"Sohn, J., et al.: Rationale-guided retrieval augmented generation for medical question answering. ArXiv:abs\/2411.00300 (2024). https:\/\/api.semanticscholar.org\/CorpusID:273798271"},{"key":"45_CR29","doi-asserted-by":"crossref","unstructured":"Steck, H., Ekanadham, C., Kallus, N.: Is cosine-similarity of embeddings really about similarity? Companion Proceedings of the ACM Web Conference 2024 (2024). https:\/\/api.semanticscholar.org\/CorpusID:268296965","DOI":"10.1145\/3589335.3651526"},{"key":"45_CR30","doi-asserted-by":"publisher","unstructured":"Tang, L., Laban, P., Durrett, G.: MiniCheck: efficient fact-checking of LLMs on grounding documents. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 8818\u20138847. Association for Computational Linguistics, Miami, Florida, USA (Nov 2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.499, https:\/\/aclanthology.org\/2024.emnlp-main.499\/","DOI":"10.18653\/v1\/2024.emnlp-main.499"},{"key":"45_CR31","volume-title":"Algorithmic Learning in a Random World","author":"V Vovk","year":"2005","unstructured":"Vovk, V., Gammerman, A., Shafer, G.: Algorithmic Learning in a Random World. Springer-Verlag, Berlin, Heidelberg (2005)"},{"key":"45_CR32","unstructured":"Walden, W.G., et al.: Auto-argue: LLM-based report generation evaluation (2025). https:\/\/api.semanticscholar.org\/CorpusID:281682210"},{"key":"45_CR33","unstructured":"Xie, Q., Li, Q., Yu, Z., Zhang, Y., Zhang, Y., Yang, L.: An empirical analysis of uncertainty in large language model evaluations. ArXiv:abs\/2502.10709 (2025). https:\/\/api.semanticscholar.org\/CorpusID:276408437"},{"key":"45_CR34","unstructured":"Xiong, M., et al.: Can LLMs express their uncertainty? an empirical evaluation of confidence elicitation in LLMs. ArXiv abs\/2306.13063 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259224389"},{"key":"45_CR35","unstructured":"Yang, X., et al.: Crag - comprehensive rag benchmark. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. NIPS \u201924, Curran Associates Inc., Red Hook, NY, USA (2025)"},{"key":"45_CR36","unstructured":"Zhang, Y., et al.: Qwen3 embedding: Advancing text embedding and reranking through foundation models. ArXiv abs\/2506.05176 (2025). https:\/\/api.semanticscholar.org\/CorpusID:279243736"}],"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_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:04:44Z","timestamp":1774357484000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21300-6_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032212993","9783032213006"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21300-6_45","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"}}]}}