{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:30:19Z","timestamp":1773520219517,"version":"3.50.1"},"reference-count":22,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGIR Forum"],"published-print":{"date-parts":[[2025,12,1]]},"abstract":"<jats:p>Retrieval-augmented generation (RAG) leverages LLMs to automatically find relevant documents and to provide users with direct answers to their queries. Supplying retrieved documents deemed to be relevant during answer generation reduces LLM \"hallucinations.\" However, as generative AI proliferates, a RAG system will increasingly find documents that have been generated as well. Although they can be useful, we observe that LLMs favor generated over authentic content during retrieval. In our research, we have shown that detecting LLM-generated content proves to be inherently more difficult than expected. Likewise, citing a source for a generated statement makes it verifiable. But it often remains unclear which sources have been discarded in favor of the cited one. We demonstrate this kind of framing in the context of product search. Direct answers often narrow the user's perspective of the available diversity of choices. The sincerity of a RAG system must therefore be judged by the authenticity of its answers.<\/jats:p>\n                  <jats:p>\n                    <jats:bold>Date:<\/jats:bold>\n                    18 July 2025.\n                  <\/jats:p>","DOI":"10.1145\/3799914.3799919","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T18:19:03Z","timestamp":1772648343000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["About Authenticity in Information Retrieval: A Keynote at ICTIR 2025"],"prefix":"10.1145","volume":"59","author":[{"given":"Martin","family":"Potthast","sequence":"first","affiliation":[{"name":"University of Kassel, hessian.AI, and ScaDS.AI, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-76941-7_83"},{"key":"e_1_2_1_2_1","first-page":"1108","volume-title":"57th Annual Meeting of the Association for Computational Linguistics (ACL","author":"Bevendorff Janek","year":"2019","unstructured":"Janek Bevendorff, Martin Potthast, Matthias Hagen, and Benno Stein. Heuristic Authorship Obfuscation. In Anna Korhonen, Llu\u00eds M\u00e0rquez, and David Traum, editors, 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019), pages 1098\u20131108. Association for Computational Linguistics, July 2019a. URL https:\/\/aclanthology.org\/P19\u20131104\/."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1068"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56063-7_4"},{"key":"e_1_2_1_5_1","first-page":"3787","volume-title":"The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)","author":"Bevendorff Janek","unstructured":"Janek Bevendorff, Matti Wiegmann, Emmelie Richter, Martin Potthast, and Benno Stein. The Two Paradigms of LLM Detection: Authorship Attribution vs. Authorship Verification. In Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, editors, The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) (Findings), pages 3762\u20133787. Association for Computational Linguistics, July 2025. ISBN 979-8-89176-256-5. URL https:\/\/aclanthology.org\/2025.findings-acl.194\/."},{"key":"e_1_2_1_6_1","volume-title":"Rowling's secret life as wizard crime writer revealed. The Sunday Times","author":"Brooks Richard","year":"2013","unstructured":"Richard Brooks. Whodunnit? J.K. Rowling's secret life as wizard crime writer revealed. The Sunday Times, 2013. URL https:\/\/web.archive.org\/web\/20130720051842\/http:\/\/www.thesundaytimes.co.uk\/sto\/news\/uk_news\/Arts\/article1287513.ece."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3386\/w34255"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/1-4020-3851-8"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1093\/llc\/fqv040"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015448"},{"key":"e_1_2_1_11_1","volume-title":"Kevin Lane Keller, and Marc Oliver Opresnik. Marketing-Management. Pearson Deutschland, 15 edition","author":"Kotler Philip","year":"2017","unstructured":"Philip Kotler, Kevin Lane Keller, and Marc Oliver Opresnik. Marketing-Management. Pearson Deutschland, 15 edition, 2017. URL https:\/\/elibrary.pearson.de\/book\/99.150005\/9783863267742."},{"key":"e_1_2_1_12_1","first-page":"22","volume-title":"September","author":"Lambert Nathan","year":"2025","unstructured":"Nathan Lambert. Chatgpt: The agentic app. Interconnects (Substack), September 2025. URL https:\/\/www.interconnects.ai\/p\/the-agentic-app. Accessed 22 Dec 2025."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_29"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451964.3451978"},{"key":"e_1_2_1_15_1","first-page":"76","volume-title":"24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Javadi Vahid Sadiri","unstructured":"Vahid Sadiri Javadi, Martin Potthast, and Lucie Flek. OpinionConv: Conversational Product Search with Grounded Opinions. In David Schlangen, Svetlana Stoyanchev, Shafiq Joty, Ondrej Dusek, Casey Kennington, and Malihe Alikhani, editors, 24th Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 66\u201376. Association for Computational Linguistics, September 2023. URL https:\/\/aclanthology.org\/2023.sigdial-1.6."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651489"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/asi.21001"},{"key":"e_1_2_1_19_1","volume-title":"KI statt Couch?","year":"2023","unstructured":"tagesschau.de. KI statt Couch?, 2023. URL https:\/\/web.archive.org\/web\/20230928063255\/https:\/\/www.tagesschau.de\/wissen\/forschung\/ki-psychotherapie-100.html."},{"key":"e_1_2_1_20_1","volume-title":"Generative engine optimization","year":"2025","unstructured":"Wikipedia. Generative engine optimization, 2025. URL https:\/\/en.wikipedia.org\/w\/index.php?title=Generative_engine_optimization&oldid=1328028469."},{"key":"e_1_2_1_21_1","volume-title":"Commercialized Generative AI: A Critical Study of the Feasibility and Ethics of Generating Native Advertising Using Large Language Models in Conversational Web Search","author":"Zelch Ines","year":"2023","unstructured":"Ines Zelch, Matthias Hagen, and Martin Potthast. Commercialized Generative AI: A Critical Study of the Feasibility and Ethics of Generating Native Advertising Using Large Language Models in Conversational Web Search. In Michael Granitzer, Christian Guetl, Christine Plote, Stefan Voigt, and Andreas Wagner, editors, 5th International Symposium on Open Search Technology (OSSYM 2023). International Open Search Symposium, October 2023. URL https:\/\/e-publishing.cern.ch\/index.php\/OSSYM."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271776"}],"container-title":["ACM SIGIR Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799914.3799919","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:19:27Z","timestamp":1773508767000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799914.3799919"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":22,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,12,1]]}},"alternative-id":["10.1145\/3799914.3799919"],"URL":"https:\/\/doi.org\/10.1145\/3799914.3799919","relation":{},"ISSN":["0163-5840"],"issn-type":[{"value":"0163-5840","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"assertion":[{"value":"2026-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}