{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T02:20:16Z","timestamp":1778034016895,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,18]]},"DOI":"10.1145\/3731120.3744606","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T13:34:06Z","timestamp":1752845646000},"page":"369-379","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluating List Construction and Temporal Understanding capabilities of Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0001-0688-7269","authenticated-orcid":false,"given":"Alexandru","family":"Dumitru","sequence":"first","affiliation":[{"name":"Prosus, Delft, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-5885-2175","authenticated-orcid":false,"given":"Venktesh","family":"V","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Delft, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-7235-0665","authenticated-orcid":false,"given":"Adam","family":"Jatowt","sequence":"additional","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-0163-0739","authenticated-orcid":false,"given":"Avishek","family":"Anand","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Delft, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2205.12665"},{"key":"e_1_3_2_1_2_1","first-page":"1877","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877-1901. https:\/\/2.zoppoz.workers.dev:443\/https\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619088"},{"key":"e_1_3_2_1_4_1","volume-title":"TableQnA: Answering List Intent Queries With Web Tables. CoRR","author":"Chakrabarti Kaushik","year":"2020","unstructured":"Kaushik Chakrabarti, Zhimin Chen, Siamak Shakeri, Guihong Cao, and Surajit Chaudhuri. 2020. TableQnA: Answering List Intent Queries With Web Tables. CoRR, Vol. abs\/2001.04828 (2020). arXiv:2001.04828 https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2001.04828"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCEA58433.2023.10135342"},{"key":"e_1_3_2_1_6_1","unstructured":"Wenhu Chen Xinyi Wang and William Yang Wang. 2021. A Dataset for Answering Time-Sensitive Questions. arxiv:2108.06314 [cs.CL]"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.637"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109134"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657834"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00459"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Simon Gottschalk and Elena Demidova. 2018. EventKG: A Multilingual Event-Centric Temporal Knowledge Graph. arxiv:1804.04526 [cs.CL]","DOI":"10.1007\/978-3-319-93417-4_18"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1460690.1460714"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661927"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1963192.1963296"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191536"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482416"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2579044"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487788.2488126"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/nyas.15125"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914805"},{"key":"e_1_3_2_1_22_1","volume-title":"Akari Asai, Xinyan Velocity Yu, Dragomir R. Radev, Noah A. Smith, Yejin Choi, and Kentaro Inui.","author":"Kasai Jungo","year":"2022","unstructured":"Jungo Kasai, Keisuke Sakaguchi, Yoichi Takahashi, Ronan Le Bras, Akari Asai, Xinyan Velocity Yu, Dragomir R. Radev, Noah A. Smith, Yejin Choi, and Kentaro Inui. 2022. RealTime QA: What's the Answer Right Now? ArXiv, Vol. abs\/2207.13332 (2022). https:\/\/2.zoppoz.workers.dev:443\/https\/api.semanticscholar.org\/CorpusID:251105205"},{"key":"e_1_3_2_1_23_1","unstructured":"Spencer Kelly. 2024. Dumpster-dip: wikipedia dump parser. https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/spencermountain\/dumpster-dip."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.616"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V37I11.26529"},{"key":"e_1_3_2_1_26_1","unstructured":"Alexandria Leto Cecilia Aguerrebere Ishwar Bhati Ted Willke Mariano Tepper and Vy Ai Vo. 2024. Toward Optimal Search and Retrieval for RAG. arxiv:2411.07396 [cs.CL] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2411.07396"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1157"},{"key":"e_1_3_2_1_29_1","volume-title":"Yassine Benajiba, and Miguel Ballesteros.","author":"Margatina Katerina","year":"2023","unstructured":"Katerina Margatina, Shuai Wang, Yogarshi Vyas, Neha Anna John, Yassine Benajiba, and Miguel Ballesteros. 2023. Dynamic benchmarking of masked language models on temporal concept drift with multiple views. arXiv preprint arXiv:2302.12297 (2023)."},{"key":"e_1_3_2_1_30_1","unstructured":"Vaibhav Mavi Anubhav Jangra and Adam Jatowt. 2022. A Survey on Multi-hop Question Answering and Generation. arxiv:2204.09140 [cs.CL]"},{"key":"e_1_3_2_1_31_1","volume-title":"Vassilis N. Ioannidis, Soji Adeshina, Phillip R. Howard, Tetiana Grinberg, Nagib Hakim, and George Karypis.","author":"Mavromatis Costas","year":"2021","unstructured":"Costas Mavromatis, Prasanna Lakkur Subramanyam, Vassilis N. Ioannidis, Soji Adeshina, Phillip R. Howard, Tetiana Grinberg, Nagib Hakim, and George Karypis. 2021. TempoQR: Temporal Question Reasoning over Knowledge Graphs. arxiv:2112.05785 [cs.CL]"},{"key":"e_1_3_2_1_32_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arxiv:2303.08774 [cs.CL]"},{"key":"e_1_3_2_1_33_1","volume-title":"100, 000 Questions for Machine Comprehension of Text. CoRR","author":"Rajpurkar Pranav","year":"2016","unstructured":"Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016a. SQuAD: 100, 000 Questions for Machine Comprehension of Text. CoRR, Vol. abs\/1606.05250 (2016). arXiv:1606.05250 https:\/\/2.zoppoz.workers.dev:443\/http\/arxiv.org\/abs\/1606.05250"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.520"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.496"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.552"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Karan Singhal Tao Tu Juraj Gottweis Rory Sayres Ellery Wulczyn Le Hou Kevin Clark Stephen Pfohl Heather Cole-Lewis Darlene Neal Mike Schaekermann Amy Wang Mohamed Amin Sami Lachgar Philip Andrew Mansfield Sushant Prakash Bradley Green Ewa Dominowska Blaise Ag\u00fcera y Arcas Nenad Tomasev Yun Liu Renee Wong Christopher Semturs S. Sara Mahdavi Joelle K. Barral Dale R. Webster Gregory S. Corrado Yossi Matias Shekoofeh Azizi Alan Karthikesalingam and Vivek Natarajan. 2023. Towards Expert-Level Medical Question Answering with Large Language Models. CoRR Vol. abs\/2305.09617 (2023). doi:10.48550\/ARXIV.2305.09617 arXiv:2305.09617","DOI":"10.48550\/ARXIV.2305.09617"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.6"},{"key":"e_1_3_2_1_40_1","unstructured":"Pat Verga Sebastian Hofstatter Sophia Althammer Yixuan Su Aleksandra Piktus Arkady Arkhangorodsky Minjie Xu Naomi White and Patrick Lewis. 2024. Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models. arxiv:2404.18796 [cs.CL] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2404.18796"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Jiexin Wang Adam Jatowt and Masatoshi Yoshikawa. 2022. ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections. arxiv:2109.03438 [cs.CL]","DOI":"10.1145\/3477495.3531734"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1093\/BIOINFORMATICS\/BTAC397"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2306.00435"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.696"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.87"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2210.14353"}],"event":{"name":"ICTIR '25: International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval","location":"Padua Italy","acronym":"ICTIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3731120.3744606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:19:02Z","timestamp":1755868742000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3731120.3744606"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,18]]},"references-count":46,"alternative-id":["10.1145\/3731120.3744606","10.1145\/3731120"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3731120.3744606","relation":{},"subject":[],"published":{"date-parts":[[2025,7,18]]},"assertion":[{"value":"2025-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}