{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:14:18Z","timestamp":1775841258182,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","funder":[{"name":"New Generation Artificial Intelligence–National Science and Technology Major Project","award":["2025ZD0123502"],"award-info":[{"award-number":["2025ZD0123502"]}]},{"name":"Australia–Indonesia Knowledge Partnership Platform (KONEKSI)","award":["1447\/CRG\/2023\/23-DU"],"award-info":[{"award-number":["1447\/CRG\/2023\/23-DU"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792597","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"2330-2338","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8598-3437","authenticated-orcid":false,"given":"Yutao","family":"Wu","sequence":"first","affiliation":[{"name":"Deakin University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8400-5754","authenticated-orcid":false,"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Deakin Universtiy, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9227-9717","authenticated-orcid":false,"given":"Yunhao","family":"Feng","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9238-8840","authenticated-orcid":false,"given":"Jiale","family":"Ding","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2099-4973","authenticated-orcid":false,"given":"Xingjun","family":"Ma","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Litsearch: A retrieval benchmark for scientific literature search. arXiv preprint arXiv:2407.18940","author":"Ajith Anirudh","year":"2024","unstructured":"Anirudh Ajith, Mengzhou Xia, Alexis Chevalier, Tanya Goyal, Danqi Chen, and Tianyu Gao. 2024. Litsearch: A retrieval benchmark for scientific literature search. arXiv preprint arXiv:2407.18940 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"How deep do large language models internalize scientific literature and citation practices? arXiv preprint arXiv:2504.02767","author":"Algaba Andres","year":"2025","unstructured":"Andres Algaba, Vincent Holst, Floriano Tori, Melika Mobini, Brecht Verbeken, Sylvia Wenmackers, and Vincent Ginis. 2025. How deep do large language models internalize scientific literature and citation practices? arXiv preprint arXiv:2504.02767 (2025)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00179"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_5_1","volume-title":"Consensus: AI Search Engine for Research. https:\/\/consensus.app\/ Accessed","year":"2025","unstructured":"Consensus. 2025. Consensus: AI Search Engine for Research. https:\/\/consensus.app\/ Accessed: September 2025."},{"key":"e_1_3_2_1_6_1","volume-title":"A dataset of information-seeking questions and answers anchored in research papers. arXiv preprint arXiv:2105.03011","author":"Dasigi Pradeep","year":"2021","unstructured":"Pradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Cohan, Noah A Smith, and Matt Gardner. 2021. A dataset of information-seeking questions and answers anchored in research papers. arXiv preprint arXiv:2105.03011 (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080730"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/276675.276685"},{"key":"e_1_3_2_1_9_1","volume-title":"Gemini Deep Research \u2014 Your Personal Research Assistant. https:\/\/gemini.google\/overview\/deep-research\/ Accessed","year":"2025","unstructured":"Google. 2025. Gemini Deep Research \u2014 Your Personal Research Assistant. https:\/\/gemini.google\/overview\/deep-research\/ Accessed: September 2025."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605764.3623985"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 11663-11679","author":"He Yichen","unstructured":"Yichen He, Guanhua Huang, Peiyuan Feng, Yuan Lin, Yuchen Zhang, Hang Li, and Weinan E. 2025. PaSa: An LLM Agent for Comprehensive Academic Paper Search. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 11663-11679."},{"key":"e_1_3_2_1_12_1","volume-title":"Llms-as-judges: a comprehensive survey on llm-based evaluation methods. arXiv preprint arXiv:2412.05579","author":"Li Haitao","year":"2024","unstructured":"Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, and Yiqun Liu. 2024. Llms-as-judges: a comprehensive survey on llm-based evaluation methods. arXiv preprint arXiv:2412.05579 (2024)."},{"key":"e_1_3_2_1_13_1","first-page":"3","article-title":"Safety at scale: A comprehensive survey of large model and agent safety","volume":"8","author":"Ma Xingjun","year":"2026","unstructured":"Xingjun Ma, Yifeng Gao, Yixu Wang, Ruofan Wang, Xin Wang, Ye Sun, Yifan Ding, Hengyuan Xu, Yunhao Chen, Yunhan Zhao, et al., 2026. Safety at scale: A comprehensive survey of large model and agent safety. Foundations and Trends in Privacy and Security, Vol. 8, 3-4 (2026), 1-240.","journal-title":"Foundations and Trends in Privacy and Security"},{"key":"e_1_3_2_1_14_1","volume-title":"Introducing Deep Research. https:\/\/openai.com\/index\/introducing-deep-research\/ Accessed","author":"AI.","year":"2025","unstructured":"OpenAI. 2025. Introducing Deep Research. https:\/\/openai.com\/index\/introducing-deep-research\/ Accessed: September 2025."},{"key":"e_1_3_2_1_15_1","unstructured":"Avery Orrall. 2025. Paper Rejected for AI Fake References Published Elsewhere with Hardly Anything Changed. https:\/\/retractionwatch.com\/2025\/06\/12\/paper-rejected-for-ai-fake-references-published-elsewhere-with-hardly-anything-changed\/."},{"key":"e_1_3_2_1_16_1","volume-title":"Semantic Scholar: AI-Powered Research Tool. https:\/\/www.semanticscholar.org\/ Accessed","author":"Scholar Semantic","year":"2025","unstructured":"Semantic Scholar. 2025. Semantic Scholar: AI-Powered Research Tool. https:\/\/www.semanticscholar.org\/ Accessed: September 2025."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714825"},{"key":"e_1_3_2_1_18_1","volume-title":"Trends in LLM-Generated Citations on arXiv. https:\/\/spylab.ai\/blog\/hallucinations\/ Accessed","author":"Lab SPY","year":"2025","unstructured":"SPY Lab. 2025. Trends in LLM-Generated Citations on arXiv. https:\/\/spylab.ai\/blog\/hallucinations\/ Accessed: September 2025."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712091"},{"key":"e_1_3_2_1_20_1","volume-title":"Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools. arXiv preprint arXiv:2502.04644","author":"Wu Junde","year":"2025","unstructured":"Junde Wu, Jiayuan Zhu, Yuyuan Liu, Min Xu, and Yueming Jin. 2025c. Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools. arXiv preprint arXiv:2502.04644 (2025)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-58551-6"},{"key":"e_1_3_2_1_22_1","volume-title":"ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking. arXiv preprint arXiv:2510.13842","author":"Wu Yutao","year":"2025","unstructured":"Yutao Wu, Xiao Liu, Yinghui Li, Yifeng Gao, Yifan Ding, Jiale Ding, Xiang Zheng, and Xingjun Ma. 2025a. ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking. arXiv preprint arXiv:2510.13842 (2025)."},{"key":"e_1_3_2_1_23_1","volume-title":"Hallucination is inevitable: An innate limitation of large language models. arXiv preprint arXiv:2401.11817","author":"Xu Ziwei","year":"2024","unstructured":"Ziwei Xu, Sanjay Jain, and Mohan Kankanhalli. 2024. Hallucination is inevitable: An innate limitation of large language models. arXiv preprint arXiv:2401.11817 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709179"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:32:18Z","timestamp":1775838738000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":24,"alternative-id":["10.1145\/3774904.3792597","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792597","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}