{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T13:24:47Z","timestamp":1783344287467,"version":"3.54.6"},"reference-count":84,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/deed.de"},{"start":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T00:00:00Z","timestamp":1757548800000},"content-version":"vor","delay-in-days":72,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/deed.de"}],"funder":[{"name":"Bundesministeriums f\u00fcr Forschung, Technologie und Raumfahrt","award":["03FHP109"],"award-info":[{"award-number":["03FHP109"]}]},{"name":"Gemeinsamen Wissenschaftskonferenz","award":["03FHP109"],"award-info":[{"award-number":["03FHP109"]}]},{"name":"Technische Hochschule K\u00f6ln"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Datenbank Spektrum"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The rapid advancement of Large Language Models (LLMs) has introduced a\u00a0paradigm shift in Information Retrieval (IR), moving beyond conventional keyword queries and ranked result lists. LLMs now play a\u00a0critical role in the evolution of IR technologies and introduce new interaction forms like Retrieval-Augmented Generation, which is a\u00a0more dynamic and interactive retrieval process that integrates various aspects of Information Access, like Question Answering, into the dialog between a\u00a0searcher and the search engine. We explore the multi-faceted impact of LLMs on IR, particularly in three distinct layers where they have become an integral part of the retrieval process, namely the retrieval system and processing pipeline that can make use of a\u00a0richer semantic representation using advanced language models, the interaction layer, and the broader IR ecosystem. For the latter, we focus on evaluation issues as well as bias, fairness, and ethical concerns. We also highlight some recent cases of using LLMs in the medical domain to demonstrate the impact on one specific domain.<\/jats:p>","DOI":"10.1007\/s13222-025-00503-x","type":"journal-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:18:09Z","timestamp":1757927889000},"page":"71-81","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Large Language Models for Information Retrieval: Challenges and Chances"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1765-2449","authenticated-orcid":false,"given":"Timo","family":"Breuer","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0302-3227","authenticated-orcid":false,"given":"Sameh","family":"Frihat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0441-6949","authenticated-orcid":false,"given":"Norbert","family":"Fuhr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2674-9509","authenticated-orcid":false,"given":"Dirk","family":"Lewandowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8817-4632","authenticated-orcid":false,"given":"Philipp","family":"Schaer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5379-5191","authenticated-orcid":false,"given":"Ralf","family":"Schenkel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,11]]},"reference":[{"key":"503_CR1","doi-asserted-by":"publisher","first-page":"1869","DOI":"10.1145\/3539618.3591960","volume-title":"SIGIR","author":"M Alaofi","year":"2023","unstructured":"Alaofi M, Gallagher L, Sanderson M et al (2023) Can generative LLms create query variants for test collections? An exploratory study. In: SIGIR. ACM, pp 1869\u20131873 https:\/\/doi.org\/10.1145\/3539618.3591960"},{"key":"503_CR2","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2412.02043","volume-title":"Future of information retrieval research in the age of generative AI. arXiv abs\/2412.02043","author":"J Allan","year":"2024","unstructured":"Allan J, Choi E, Lopresti DP et al (2024) Future of information retrieval research in the age of generative AI. arXiv abs\/2412.02043 https:\/\/doi.org\/10.48550\/ARXIV.2412.02043"},{"key":"503_CR3","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1007\/978-3-031-56069-9_57","volume-title":"ECIR (5), lecture notes in computer science","author":"L Azzopardi","year":"2024","unstructured":"Azzopardi L, Clarke CLA, Kantor PB et al (2024) The search futures workshop. In: ECIR (5), lecture notes in computer science. Springer, pp 422\u2013425 https:\/\/doi.org\/10.1007\/978-3-031-56069-9_57"},{"key":"503_CR4","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1145\/3674127.3674138","volume-title":"Bias in retrieval systems. In: information retrieval: advanced topics and techniques","author":"R Baeza-Yates","year":"2024","unstructured":"Baeza-Yates R, Murgai L, Dudy S (2024) Bias in retrieval systems. In: information retrieval: advanced topics and techniques, 1st\u00a0edn. Association for Computing Machinery, New York, NY, USA, pp 389\u2013444 https:\/\/doi.org\/10.1145\/3674127.3674138","edition":"1"},{"key":"503_CR5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.19092","volume-title":"Rankers, judges, and assistants: towards understanding the interplay of LLms in information retrieval evaluation. arxiv abs\/2503.19092","author":"K Balog","year":"2025","unstructured":"Balog K, Metzler D, Qin Z (2025) Rankers, judges, and assistants: towards understanding the interplay of LLms in information retrieval evaluation. arxiv abs\/2503.19092 https:\/\/doi.org\/10.48550\/ARXIV.2503.19092"},{"key":"503_CR6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.14346","volume-title":"DISC-MedLLM: bridging general large language models and real-world medical consultation. arxiv abs\/2308.14346","author":"Z Bao","year":"2023","unstructured":"Bao Z, Chen W, Xiao S et al (2023) DISC-MedLLM: bridging general large language models and real-world medical consultation. arxiv abs\/2308.14346 https:\/\/doi.org\/10.48550\/ARXIV.2308.14346"},{"issue":"8","key":"503_CR7","doi-asserted-by":"publisher","first-page":"53","DOI":"10.4230\/DagRep.14.8.53","volume":"14","author":"C Bauer","year":"2025","unstructured":"Bauer C, Chen L, Ferro N et al (2025) Conversational agents: a\u00a0framework for evaluation (CAFE) (Dagstuhl perspectives workshop 24352). Dagstuhl Rep 14(8):53\u201358. https:\/\/doi.org\/10.4230\/DagRep.14.8.53","journal-title":"Dagstuhl Rep"},{"issue":"2","key":"503_CR8","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1177\/0165551508095781","volume":"35","author":"D Bawden","year":"2009","unstructured":"Bawden D, Robinson L (2009) The dark side of information: overload, anxiety and other paradoxes and pathologies. J\u00a0Inf Sci 35(2):180\u2013191. https:\/\/doi.org\/10.1177\/0165551508095781","journal-title":"J Inf Sci"},{"key":"503_CR9","doi-asserted-by":"publisher","first-page":"e64364","DOI":"10.2196\/64364","volume":"27","author":"E Berman","year":"2025","unstructured":"Berman E, Sundberg MH, Bitzer M et al (2025) Retrieval augmented therapy suggestion for molecular tumor boards: algorithmic development and validation study. J\u00a0Med Internet Res 27:e64364. https:\/\/doi.org\/10.2196\/64364","journal-title":"J Med Internet Res"},{"key":"503_CR10","first-page":"2206","volume-title":"ICML, proceedings of machine learning research","author":"S Borgeaud","year":"2022","unstructured":"Borgeaud S, Mensch A, Hoffmann J et al (2022) Improving language models by retrieving from trillions of tokens. In: ICML, proceedings of machine learning research. PMLR, pp 2206\u20132240"},{"key":"503_CR11","doi-asserted-by":"publisher","first-page":"17709","DOI":"10.1609\/AAAI.V38I16.29723","volume-title":"AAAI","author":"Y Cai","year":"2024","unstructured":"Cai Y, Wang L, Wang Y et al (2024) Medbench: a\u00a0large-scale chinese benchmark for evaluating medical large language models. In: AAAI. AAAI Press, pp 17709\u201317717 https:\/\/doi.org\/10.1609\/AAAI.V38I16.29723"},{"issue":"5","key":"503_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3704262","volume":"57","author":"Y Cao","year":"2025","unstructured":"Cao Y, Li S, Liu Y et al (2025) A survey of AI-generated content (AIGC). ACM Comput Surv 57(5):1\u2013125. https:\/\/doi.org\/10.1145\/3704262","journal-title":"ACM Comput Surv"},{"key":"503_CR13","doi-asserted-by":"publisher","first-page":"14930","DOI":"10.18653\/V1\/2024.ACL-LONG.798","volume-title":"ACL (1). Association for computational linguistics","author":"X Chen","year":"2024","unstructured":"Chen X, He B, Lin H et al (2024) Spiral of silence: how is large language model killing information retrieval?\u2014A case study on open domain question answering. In: ACL (1). Association for computational linguistics, pp 14930\u201314951 https:\/\/doi.org\/10.18653\/V1\/2024.ACL-LONG.798"},{"key":"503_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-0171-6","volume-title":"Language modeling for information retrieval","year":"2003","unstructured":"Croft WB, Lafferty J (eds) (2003) Language modeling for information retrieval. Springer, Netherlands https:\/\/doi.org\/10.1007\/978-94-017-0171-6"},{"key":"503_CR15","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1145\/3626772.3657834","volume-title":"SIGIR","author":"F Cuconasu","year":"2024","unstructured":"Cuconasu F, Trappolini G, Siciliano F et al (2024) The power of noise: redefining retrieval for RAG systems. In: SIGIR. ACM, pp 719\u2013729 https:\/\/doi.org\/10.1145\/3626772.3657834"},{"key":"503_CR16","doi-asserted-by":"publisher","first-page":"6437","DOI":"10.1145\/3637528.3671458","volume-title":"KDD","author":"S Dai","year":"2024","unstructured":"Dai S, Xu C, Xu S et al (2024a) Bias and unfairness in information retrieval systems: new challenges in the LLM era. In: KDD. ACM, pp 6437\u20136447 https:\/\/doi.org\/10.1145\/3637528.3671458"},{"key":"503_CR17","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1145\/3637528.3671882","volume-title":"KDD","author":"S Dai","year":"2024","unstructured":"Dai S, Zhou Y, Pang L et al (2024b) Neural retrievers are biased towards llm-generated content. In: KDD. ACM, pp 526\u2013537 https:\/\/doi.org\/10.1145\/3637528.3671882"},{"key":"503_CR18","doi-asserted-by":"publisher","first-page":"4171","DOI":"10.18653\/V1\/N19-1423","volume-title":"NAACL-HLT (1). Association for computational linguistics","author":"J Devlin","year":"2019","unstructured":"Devlin J, Chang M, Lee K et al (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (1). Association for computational linguistics, pp 4171\u20134186 https:\/\/doi.org\/10.18653\/V1\/N19-1423"},{"key":"503_CR19","doi-asserted-by":"publisher","first-page":"1963","DOI":"10.1145\/3626772.3657871","volume-title":"SIGIR","author":"L Dietz","year":"2024","unstructured":"Dietz L (2024) A workbench for autograding retrieve\/generate systems. In: SIGIR. ACM, pp 1963\u20131972 https:\/\/doi.org\/10.1145\/3626772.3657871"},{"key":"503_CR20","first-page":"23787","volume-title":"Proceedings of the AAAI conference on artificial intelligence","author":"Y Ding","year":"2025","unstructured":"Ding Y, Facciani M, Joyce E et al (2025) Citations and trust in llm generated responses. In: Proceedings of the AAAI conference on artificial intelligence, pp 23787\u201323795"},{"key":"503_CR21","doi-asserted-by":"publisher","first-page":"e67143","DOI":"10.2196\/67143","volume":"27","author":"F Eisinger","year":"2025","unstructured":"Eisinger F, Holderried F, Mahling M et al (2025) What\u2019s going on with me and how can I better manage my health? The potential of GPT-4 to transform discharge letters into patient-centered letters to enhance patient safety: prospective, exploratory study. J\u00a0Med Internet Res 27:e67143. https:\/\/doi.org\/10.2196\/67143","journal-title":"J Med Internet Res"},{"key":"503_CR22","doi-asserted-by":"publisher","first-page":"14925","DOI":"10.18653\/v1\/2024.findings-emnlp.877","volume-title":"EMNLP (findings)","author":"B Engelmann","year":"2024","unstructured":"Engelmann B, Kreutz C, Haak F et al (2024) ARTS: assessing readability & text simplicity. In: EMNLP (findings), pp 14925\u201314942 https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.877"},{"issue":"4","key":"503_CR23","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/3624730","volume":"67","author":"G Faggioli","year":"2024","unstructured":"Faggioli G, Dietz L, Clarke CLA et al (2024) Who determines what is relevant? Humans or AI? Why not both? Commun ACM 67(4):31\u201334. https:\/\/doi.org\/10.1145\/3624730","journal-title":"Commun ACM"},{"issue":"1","key":"503_CR24","doi-asserted-by":"publisher","first-page":"93","DOI":"10.54195\/irrj.19784","volume":"1","author":"S Frihat","year":"2025","unstructured":"Frihat S, Fuhr N (2025) Supporting evidence-based medicine by finding both relevant and significant works. Inf Retr Res 1(1):93\u2013108. https:\/\/doi.org\/10.54195\/irrj.19784","journal-title":"Inf Retr Res"},{"key":"503_CR25","doi-asserted-by":"publisher","first-page":"2311","DOI":"10.1145\/3626772.3657974","volume-title":"SIGIR","author":"B Geng","year":"2024","unstructured":"Geng B, Huan Z, Zhang X et al (2024) Breaking the length barrier: LLM-enhanced CTR prediction in long textual user behaviors. In: SIGIR. ACM, pp 2311\u20132315 https:\/\/doi.org\/10.1145\/3626772.3657974"},{"key":"503_CR26","doi-asserted-by":"publisher","first-page":"1916","DOI":"10.1145\/3626772.3657849","volume-title":"SIGIR","author":"L Gienapp","year":"2024","unstructured":"Gienapp L, Scells H, Deckers N et al (2024) Evaluating generative ad hoc information retrieval. In: SIGIR. ACM, pp 1916\u20131929 https:\/\/doi.org\/10.1145\/3626772.3657849"},{"key":"503_CR27","volume-title":"Care: aligning language models for regional cultural awareness. arxiv preprint arxiv:250405154","author":"G Guo","year":"2025","unstructured":"Guo G, Naous T, Wakaki H et al (2025) Care: aligning language models for regional cultural awareness. arxiv preprint arxiv:250405154"},{"key":"503_CR28","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1145\/3630744.3658415","volume-title":"Websci (companion)","author":"F Haak","year":"2024","unstructured":"Haak F, Engelmann B, Kreutz CK et al (2024) Investigating bias in political search query suggestions by relative comparison with LLms. In: Websci (companion). ACM, pp 5\u20137 https:\/\/doi.org\/10.1145\/3630744.3658415"},{"key":"503_CR29","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14925640","volume-title":"18. Internationales symposium F\u00fcr Informationswissenschaft (ISI 2025)","author":"H H\u00e4u\u00dfler","year":"2025","unstructured":"H\u00e4u\u00dfler H (2025) Doktor Google und mister Finanzchef Google sind nicht immer die besten Freunde\u201d Eine kontrollierte Laborstudie zum Vertrauen in Suchmaschinen. In: 18. Internationales symposium F\u00fcr Informationswissenschaft (ISI 2025). H\u00fclsbusch, Gl\u00fcckstadt https:\/\/doi.org\/10.5281\/zenodo.14925640"},{"issue":"1","key":"503_CR30","doi-asserted-by":"publisher","first-page":"e59213","DOI":"10.2196\/59213","volume":"10","author":"F Holderried","year":"2024","unstructured":"Holderried F, Stegemann-Philipps C, Herrmann-Werner A et al (2024) A language model-powered simulated patient with automated feedback for history taking: prospective study. Jmir Med Educ 10(1):e59213. https:\/\/doi.org\/10.2196\/59213","journal-title":"Jmir Med Educ"},{"key":"503_CR31","unstructured":"Ja\u017awi\u0144ska K, Chandrasekar A (2025) AI search has a\u00a0citation problem. https:\/\/www.cjr.org\/tow_center\/we-compared-eight-ai-search-engines-theyre-all-bad-at-citing-news.php. Accessed 18-03-2025"},{"issue":"12","key":"503_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji Z, Lee N, Frieske R et al (2023) Survey of hallucination in natural language generation. ACM Comput Surv 55(12):1\u2013248","journal-title":"ACM Comput Surv"},{"key":"503_CR33","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-031-56069-9_63","volume-title":"ECIR","author":"J Karlgren","year":"2024","unstructured":"Karlgren J, D\u00fcrlich L, Gogoulou E et al (2024) Eloquent clef shared tasks for evaluation of generative language model quality. In: ECIR, pp 459\u2013465 https:\/\/doi.org\/10.1007\/978-3-031-56069-9_63"},{"key":"503_CR34","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.1145\/3626772.3657798","volume-title":"SIGIR","author":"E Khramtsova","year":"2024","unstructured":"Khramtsova E, Zhuang S, Baktashmotlagh M et al (2024) Leveraging LLms for unsupervised dense retriever ranking. In: SIGIR. ACM, pp 1307\u20131317 https:\/\/doi.org\/10.1145\/3626772.3657798"},{"key":"503_CR35","doi-asserted-by":"publisher","first-page":"11968","DOI":"10.18653\/V1\/2024.FINDINGS-ACL.712","volume-title":"ACL (findings)","author":"C Kreutz","year":"2024","unstructured":"Kreutz C, Haak F, Engelmann B et al (2024) BATS: benchmarking text simplicity. In: ACL (findings), pp 11968\u201311989 https:\/\/doi.org\/10.18653\/V1\/2024.FINDINGS-ACL.712"},{"key":"503_CR36","volume-title":"Reinforcement learning for optimizing rag for domain chatbots. arxiv preprint arxiv:240106800","author":"M Kulkarni","year":"2024","unstructured":"Kulkarni M, Tangarajan P, Kim K et al (2024) Reinforcement learning for optimizing rag for domain chatbots. arxiv preprint arxiv:240106800"},{"key":"503_CR37","volume-title":"NeurIPS","author":"PSH Lewis","year":"2020","unstructured":"Lewis PSH, Perez E, Piktus A et al (2020) Retrieval-augmented generation for knowledge-intensive NLP tasks. In: NeurIPS (https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6b493230205f780e1bc26945df7481e5-Abstract.html)"},{"key":"503_CR38","first-page":"6705","volume-title":"COLING","author":"S Li","year":"2025","unstructured":"Li S, Stenzel L, Eickhoff C et al (2025) Enhancing retrieval-augmented generation: a\u00a0study of best practices. In: COLING. Association for Computational Linguistics, pp 6705\u20136717"},{"key":"503_CR39","volume-title":"Graph-based confidence calibration for large language models. arxiv preprint arxiv:241102454","author":"Y Li","year":"2024","unstructured":"Li Y, Wang S, Huang L et al (2024) Graph-based confidence calibration for large language models. arxiv preprint arxiv:241102454"},{"key":"503_CR40","volume-title":"Paper copilot: a\u00a0self-evolving and efficient llm system for personalized academic assistance. arxiv preprint arxiv:240904593","author":"G Lin","year":"2024","unstructured":"Lin G, Feng T, Han P et al (2024) Paper copilot: a\u00a0self-evolving and efficient llm system for personalized academic assistance. arxiv preprint arxiv:240904593"},{"key":"503_CR41","doi-asserted-by":"publisher","DOI":"10.2200\/S01123ED1V01Y202108HLT053","volume-title":"Pretrained transformers for text ranking: BERT and beyond. Synthesis lectures on human language technologies","author":"J Lin","year":"2021","unstructured":"Lin J, Nogueira R, Yates A (2021) Pretrained transformers for text ranking: BERT and beyond. Synthesis lectures on human language technologies. Morgan & Claypool Publishers https:\/\/doi.org\/10.2200\/S01123ED1V01Y202108HLT053"},{"key":"503_CR42","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1145\/3404835.3463064","volume-title":"SIGIR","author":"B Liu","year":"2021","unstructured":"Liu B, Wu Y, Liu Y et al (2021) Conversational vs traditional: comparing search behavior and outcome in legal case retrieval. In: SIGIR. ACM, pp 1622\u20131626 https:\/\/doi.org\/10.1145\/3404835.3463064"},{"key":"503_CR43","volume-title":"A survey of personalized large language models: progress and future directions. arxiv preprint arxiv:250211528","author":"J Liu","year":"2025","unstructured":"Liu J, Qiu Z, Li Z et al (2025a) A survey of personalized large language models: progress and future directions. arxiv preprint arxiv:250211528"},{"key":"503_CR44","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1162\/TACL_A_00638","volume":"12","author":"NF Liu","year":"2024","unstructured":"Liu NF, Lin K, Hewitt J et al (2024) Lost in the middle: how language models use long contexts. Trans Assoc Comput Linguistics 12:157\u2013173. https:\/\/doi.org\/10.1162\/TACL_A_00638","journal-title":"Trans Assoc Comput Linguistics"},{"key":"503_CR45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.09940","volume-title":"Passage segmentation of documents for extractive question answering. arxiv abs\/2501.09940","author":"Z Liu","year":"2025","unstructured":"Liu Z, Simon C, Caspani F (2025b) Passage segmentation of documents for extractive question answering. arxiv abs\/2501.09940 https:\/\/doi.org\/10.48550\/ARXIV.2501.09940"},{"key":"503_CR46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.11885","volume-title":"Med-R2: crafting trustworthy LLM physicians through retrieval and reasoning of evidence-based medicine. arxiv abs\/2501.11885","author":"K Lu","year":"2025","unstructured":"Lu K, Liang Z, Pan D et al (2025) Med-R2: crafting trustworthy LLM physicians through retrieval and reasoning of evidence-based medicine. arxiv abs\/2501.11885 https:\/\/doi.org\/10.48550\/ARXIV.2501.11885"},{"key":"503_CR47","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1145\/3626772.3657850","volume-title":"SIGIR","author":"W Mansour","year":"2024","unstructured":"Mansour W, Zhuang S, Zuccon G et al (2024) Revisiting document expansion and filtering for effective first-stage retrieval. In: SIGIR. ACM, pp 186\u2013196 https:\/\/doi.org\/10.1145\/3626772.3657850"},{"issue":"4","key":"503_CR48","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1145\/1121949.1121979","volume":"49","author":"G Marchionini","year":"2006","unstructured":"Marchionini G (2006) Exploratory search: from finding to understanding. Commun ACM 49(4):41\u201346. https:\/\/doi.org\/10.1145\/1121949.1121979","journal-title":"Commun ACM"},{"key":"503_CR49","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1145\/3626772.3657846","volume-title":"SIGIR","author":"J Mayfield","year":"2024","unstructured":"Mayfield J, Yang E, Lawrie DJ et al (2024) On the evaluation of machine-generated reports. In: SIGIR. ACM, pp 1904\u20131915 https:\/\/doi.org\/10.1145\/3626772.3657846"},{"issue":"1","key":"503_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3476415.3476428","volume":"55","author":"D Metzler","year":"2021","unstructured":"Metzler D, Tay Y, Bahri D et al (2021) Rethinking search: making domain experts out of dilettantes. SIGIR Forum 55(1):1\u201313. https:\/\/doi.org\/10.1145\/3476415.3476428","journal-title":"SIGIR Forum"},{"key":"503_CR51","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1145\/3539618.3591871","volume-title":"Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval, SIGIR 2023","author":"M Najork","year":"2023","unstructured":"Najork M (2023) Generative information retrieval. In: Chen H, Duh WE, Huang H et al (eds) Proceedings of the 46th international ACM SIGIR conference on research and development in information retrieval, SIGIR 2023. ACM, Taipei, Taiwan, pp 23\u201327 https:\/\/doi.org\/10.1145\/3539618.3591871"},{"key":"503_CR52","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1145\/3669940.3707264","volume-title":"ASPLOS (1)","author":"D Quinn","year":"2025","unstructured":"Quinn D, Nouri M, Patel N et al (2025) Accelerating retrieval-augmented generation. In: ASPLOS (1). ACM, pp 15\u201332 https:\/\/doi.org\/10.1145\/3669940.3707264"},{"key":"503_CR53","volume-title":"NeurIPS","author":"R Rafailov","year":"2023","unstructured":"Rafailov R, Sharma A, Mitchell E et al (2023) Direct preference optimization: your language model is secretly a\u00a0reward model. In: NeurIPS (http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html)"},{"key":"503_CR54","doi-asserted-by":"publisher","first-page":"3040","DOI":"10.1145\/3626772.3657992","volume-title":"SIGIR","author":"HA Rahmani","year":"2024","unstructured":"Rahmani HA, Siro C, Aliannejadi M et al (2024) LLM4Eval: large language model for evaluation in IR. In: SIGIR. ACM, pp 3040\u20133043 https:\/\/doi.org\/10.1145\/3626772.3657992"},{"key":"503_CR55","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1145\/3701551.3705706","volume-title":"WSDM","author":"HA Rahmani","year":"2025","unstructured":"Rahmani HA, Siro C, Aliannejadi M et al (2025) LLM4Eval@WSDM 2025: large language model for evaluation in information retrieval. In: WSDM. ACM, pp 1120\u20131121 https:\/\/doi.org\/10.1145\/3701551.3705706"},{"issue":"1","key":"503_CR56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3636341.3636347","volume":"57","author":"T Sakai","year":"2023","unstructured":"Sakai T (2023) On a\u00a0few responsibilities of (IR) researchers (fairness, awareness, and sustainability): a\u00a0keynote at ECIR 2023. SIGIR Forum 57(1):1\u20134. https:\/\/doi.org\/10.1145\/3636341.3636347","journal-title":"SIGIR Forum"},{"key":"503_CR57","first-page":"3784","volume-title":"EMNLP (findings)","author":"K Shuster","year":"2021","unstructured":"Shuster K, Poff S, Chen M et al (2021) Retrieval augmentation reduces hallucination in conversation. In: EMNLP (findings). Association for Computational Linguistics, pp 3784\u20133803"},{"key":"503_CR58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2409.15133","volume-title":"Don\u2019t use LLms to make relevance judgments. arxiv abs\/2409.15133","author":"I Soboroff","year":"2024","unstructured":"Soboroff I (2024a) Don\u2019t use LLms to make relevance judgments. arxiv abs\/2409.15133 https:\/\/doi.org\/10.48550\/ARXIV.2409.15133"},{"key":"503_CR59","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1145\/3674127.3674139","volume-title":"Information retrieval: advanced topics and techniques, ACM books","author":"I Soboroff","year":"2024","unstructured":"Soboroff I (2024b) Privacy in information retrieval. In: Alonso O, Baeza-Yates R (eds) Information retrieval: advanced topics and techniques, ACM books. ACM, pp 445\u2013463 https:\/\/doi.org\/10.1145\/3674127.3674139"},{"key":"503_CR60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.16148","volume-title":"The media bias taxonomy: a\u00a0systematic literature review on the forms and automated detection of media bias. arxiv abs\/2312.16148","author":"T Spinde","year":"2023","unstructured":"Spinde T, Hinterreiter S, Haak F et al (2023) The media bias taxonomy: a\u00a0systematic literature review on the forms and automated detection of media bias. arxiv abs\/2312.16148 https:\/\/doi.org\/10.48550\/ARXIV.2312.16148"},{"key":"503_CR61","doi-asserted-by":"publisher","first-page":"14918","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.923","volume-title":"EMNLP","author":"W Sun","year":"2023","unstructured":"Sun W, Yan L, Ma X et al (2023) Is chatGPT good at search? Investigating large language models as re-ranking agents. In: EMNLP. Association for Computational Linguistics, pp 14918\u201314937 https:\/\/doi.org\/10.18653\/V1\/2023.EMNLP-MAIN.923"},{"key":"503_CR62","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2411.06877","volume-title":"LLM-assisted relevance assessments: when should we ask LLms for help? arxiv abs\/2411.06877","author":"R Takehi","year":"2024","unstructured":"Takehi R, Voorhees EM, Sakai T et al (2024) LLM-assisted relevance assessments: when should we ask LLms for help? arxiv abs\/2411.06877 https:\/\/doi.org\/10.48550\/ARXIV.2411.06877"},{"key":"503_CR63","doi-asserted-by":"publisher","first-page":"251","DOI":"10.5860\/crl.76.3.251","volume":"76","author":"RS Taylor","year":"1968","unstructured":"Taylor RS (1968) Question-negotiation and information seeking in libraries. Coll Res Libr 76:251\u2013267","journal-title":"Coll Res Libr"},{"issue":"8","key":"503_CR64","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu AJ, Ting DSJ, Elangovan K et al (2023) Large language models in medicine. Nat Med 29(8):1930\u20131940. https:\/\/doi.org\/10.1038\/s41591-023-02448-8","journal-title":"Nat Med"},{"key":"503_CR65","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1145\/3626772.3657707","volume-title":"SIGIR","author":"P Thomas","year":"2024","unstructured":"Thomas P, Spielman S, Craswell N et al (2024) Large language models can accurately predict searcher preferences. In: SIGIR. ACM, pp 1930\u20131940 https:\/\/doi.org\/10.1145\/3626772.3657707"},{"key":"503_CR66","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1145\/3674127.3674135","volume-title":"Information retrieval: advanced topics and techniques, ACM books","author":"JR Trippas","year":"2024","unstructured":"Trippas JR (2024a) Conversational search. In: Information retrieval: advanced topics and techniques, ACM books. ACM, pp 285\u2013319"},{"key":"503_CR67","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1145\/3674127.3674135","volume-title":"Information retrieval: advanced topics and techniques, ACM books","author":"JR Trippas","year":"2024","unstructured":"Trippas JR (2024b) Conversational search. In: Information retrieval: advanced topics and techniques, ACM books. ACM, pp 285\u2013319 https:\/\/doi.org\/10.1145\/3674127.3674135"},{"key":"503_CR68","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-031-73147-1_4","volume-title":"Information access in the era of generative AI","author":"JR Trippas","year":"2025","unstructured":"Trippas JR, Spina D, Scholer F (2025) Adapting generative information retrieval systems to users, tasks, and scenarios. In: Information access in the era of generative AI. Springer Nature Switzerland, Cham, pp 73\u2013109 https:\/\/doi.org\/10.1007\/978-3-031-73147-1_4"},{"key":"503_CR69","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.06519","volume-title":"UMBRELA: umbrela is the (open-source reproduction of the) bing relevance assessor. arxiv abs\/2406.06519","author":"S Upadhyay","year":"2024","unstructured":"Upadhyay S, Pradeep R, Thakur N et al (2024) UMBRELA: umbrela is the (open-source reproduction of the) bing relevance assessor. arxiv abs\/2406.06519 https:\/\/doi.org\/10.48550\/ARXIV.2406.06519"},{"key":"503_CR70","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: NIPS, pp 5998\u20136008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html. Accessed: 24.07.2025"},{"key":"503_CR71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2402.17887","volume-title":"JMLR: joint medical LLM and retrieval training for enhancing reasoning and professional question answering capability. arxiv abs\/2402.17887","author":"J Wang","year":"2024","unstructured":"Wang J, Yang Z, Yao Z et al (2024a) JMLR: joint medical LLM and retrieval training for enhancing reasoning and professional question answering capability. arxiv abs\/2402.17887 https:\/\/doi.org\/10.48550\/ARXIV.2402.17887"},{"key":"503_CR72","first-page":"1","volume-title":"ACM SIGIR forum","author":"L Wang","year":"2024","unstructured":"Wang L, Yang N, Huang X et al (2024b) Large search model: redefining search stack in the era of llms. In: ACM SIGIR forum. ACM, New York, NY, USA, pp 1\u201316"},{"key":"503_CR73","doi-asserted-by":"publisher","first-page":"2492","DOI":"10.1145\/3626772.3657949","volume-title":"SIGIR","author":"S Wang","year":"2024","unstructured":"Wang S, Zhuang S, Zuccon G (2024c) Large language models based stemming for information retrieval: promises, pitfalls and failures. In: SIGIR. ACM, pp 2492\u20132496 https:\/\/doi.org\/10.1145\/3626772.3657949"},{"key":"503_CR74","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139525305","volume-title":"Interactions with search systems","author":"RW White","year":"2016","unstructured":"White RW (2016) Interactions with search systems. Cambridge University Press https:\/\/doi.org\/10.1017\/CBO9781139525305"},{"issue":"9","key":"503_CR75","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/3655615","volume":"67","author":"RW White","year":"2024","unstructured":"White RW (2024) Advancing the search frontier with AI agents. Commun ACM 67(9):54\u201365. https:\/\/doi.org\/10.1145\/3655615","journal-title":"Commun ACM"},{"key":"503_CR76","first-page":"445","volume-title":"International conference on case-based reasoning","author":"N Wiratunga","year":"2024","unstructured":"Wiratunga N, Abeyratne R, Jayawardena L et al (2024) Cbr-rag: case-based reasoning for retrieval augmented generation in llms for legal question answering. In: International conference on case-based reasoning. Springer, pp 445\u2013460"},{"key":"503_CR77","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.14732","volume-title":"Search-in-the-chain: towards the accurate, credible and traceable content generation for complex knowledge-intensive tasks. arxiv abs\/2304.14732","author":"S Xu","year":"2023","unstructured":"Xu S, Pang L, Shen H et al (2023) Search-in-the-chain: towards the accurate, credible and traceable content generation for complex knowledge-intensive tasks. arxiv abs\/2304.14732 https:\/\/doi.org\/10.48550\/ARXIV.2304.14732"},{"key":"503_CR78","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1145\/3626772.3657746","volume-title":"SIGIR","author":"H Zeng","year":"2024","unstructured":"Zeng H, Luo C, Zamani H (2024) Planning ahead in generative retrieval: guiding autoregressive generation through simultaneous decoding. In: SIGIR. ACM, pp 469\u2013480 https:\/\/doi.org\/10.1145\/3626772.3657746"},{"key":"503_CR79","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1145\/3626772.3657848","volume-title":"SIGIR","author":"C Zhai","year":"2024","unstructured":"Zhai C (2024) Large language models and future of information retrieval: opportunities and challenges. In: SIGIR. ACM, pp 481\u2013490 https:\/\/doi.org\/10.1145\/3626772.3657848"},{"key":"503_CR80","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1145\/3626772.3657963","volume-title":"SIGIR","author":"E Zhang","year":"2024","unstructured":"Zhang E, Wang X, Gong P et al (2024a) Usimagent: large language models for simulating search users. In: SIGIR. ACM, pp 2687\u20132692 https:\/\/doi.org\/10.1145\/3626772.3657963"},{"key":"503_CR81","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1145\/3626772.3657797","volume-title":"SIGIR","author":"P Zhang","year":"2024","unstructured":"Zhang P, Liu Z, Zhou Y et al (2024b) Generative retrieval via term set generation. In: SIGIR. ACM, pp 458\u2013468 https:\/\/doi.org\/10.1145\/3626772.3657797"},{"key":"503_CR82","volume-title":"NeurIPS","author":"L Zheng","year":"2023","unstructured":"Zheng L, Chiang W, Sheng Y et al (2023) Judging LLM-as-a-judge with MT-bench and Chatbot arena. In: NeurIPS (http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/91f18a1287b398d378ef22505bf41832-Abstract-Datasets_and_Benchmarks.html)"},{"key":"503_CR83","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.05112","volume-title":"A survey of large language models in medicine: progress, application, and challenge. arxiv abs\/2311.05112","author":"H Zhou","year":"2023","unstructured":"Zhou H, Gu B, Zou X et al (2023) A survey of large language models in medicine: progress, application, and challenge. arxiv abs\/2311.05112 https:\/\/doi.org\/10.48550\/ARXIV.2311.05112"},{"key":"503_CR84","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.07107","volume-title":"Large language models for information retrieval: A\u00a0survey. arXiv abs\/2308.07107","author":"Y Zhu","year":"2023","unstructured":"Zhu Y, Yuan H, Wang S et al (2023) Large language models for information retrieval: A\u00a0survey. arXiv abs\/2308.07107 https:\/\/doi.org\/10.48550\/ARXIV.2308.07107"}],"container-title":["Datenbank-Spektrum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13222-025-00503-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13222-025-00503-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13222-025-00503-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:14:57Z","timestamp":1761326097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13222-025-00503-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":84,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["503"],"URL":"https:\/\/doi.org\/10.1007\/s13222-025-00503-x","relation":{},"ISSN":["1618-2162","1610-1995"],"issn-type":[{"value":"1618-2162","type":"print"},{"value":"1610-1995","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"31 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"T.\u00a0Breuer, S.\u00a0Frihat, N.\u00a0Fuhr, D.\u00a0Lewandowski, P.\u00a0Schaer and R.\u00a0Schenkel declare that they have no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}