{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:10:19Z","timestamp":1784139019574,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Australian Research Council","award":["DP190101113"],"award-info":[{"award-number":["DP190101113"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809883","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3743-3747","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["On the Robustness of LLM Re-Rankings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1022-9904","authenticated-orcid":false,"given":"Reyhaneh","family":"Goli","sequence":"first","affiliation":[{"name":"The University of Melbourne, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6638-0232","authenticated-orcid":false,"given":"Alistair","family":"Moffat","sequence":"additional","affiliation":[{"name":"The University of Melbourne, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730159"},{"key":"e_1_3_2_1_2_1","volume-title":"Towards reproducible LLM evaluation: Quantifying uncertainty in LLM benchmark scores. CoRR., abs\/2410.03492","author":"Blackwell R. E.","year":"2024","unstructured":"R. E. Blackwell, J. Barry, and A. G. Cohn. Towards reproducible LLM evaluation: Quantifying uncertainty in LLM benchmark scores. CoRR., abs\/2410.03492, 2024."},{"key":"e_1_3_2_1_3_1","volume-title":"Does prompt formatting have any impact on LLM performance? CoRR., abs\/2411.10541","author":"He J.","year":"2024","unstructured":"J. He, M. Rungta, D. Koleczek, A. Sekhon, F. X. Wang, and S. Hasan. Does prompt formatting have any impact on LLM performance? CoRR., abs\/2411.10541, 2024."},{"issue":"4","key":"e_1_3_2_1_4_1","first-page":"422","volume":"20","author":"J\u00e4rvelin K.","year":"2002","unstructured":"K. J\u00e4rvelin and J. Kek\u00e4l\u00e4inen. Cumulated gain-based evaluation of IR techniques. ACMTrans. Inf. Sys., 20(4):422-446, 2002.","journal-title":"Cumulated gain-based evaluation of IR techniques. ACMTrans. Inf. Sys."},{"key":"e_1_3_2_1_5_1","first-page":"22199","volume":"35","author":"Kojima T.","year":"2022","unstructured":"T. Kojima, S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa. Large language models are zero-shot reasoners. J. Adv. Neural. Inf. Process. Syst., 35:22199-22213, 2022.","journal-title":"Large language models are zero-shot reasoners. J. Adv. Neural. Inf. Process. Syst."},{"key":"e_1_3_2_1_6_1","volume-title":"Holistic evaluation of language models. CoRR., abs\/2211\/09110","author":"Liang P.","year":"2022","unstructured":"P. Liang, R. Bommasani, T. Lee, D. Tsipras, D. Soylu, M. Yasunaga, Y. Zhang, D. Narayanan, Y. Wu, A. Kumar, and with 40 other authors. Holistic evaluation of language models. CoRR., abs\/2211\/09110, 2022."},{"key":"e_1_3_2_1_7_1","volume-title":"Zero-shot listwise document reranking with a large language model. CoRR., abs\/2305.02156","author":"Ma X.","year":"2023","unstructured":"X. Ma, X. Zhang, R. Pradeep, and J. Lin. Zero-shot listwise document reranking with a large language model. CoRR., abs\/2305.02156, 2023."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-45068-6_1"},{"key":"e_1_3_2_1_9_1","first-page":"708","volume-title":"Proc. EMNLP Findings","author":"Nogueira R. F.","year":"2020","unstructured":"R. F. Nogueira, Z. Jiang, R. Pradeep, and J. Lin. Document ranking with a pre trained sequence-to-sequence model. In Proc. EMNLP Findings, pages 708-718, 2020."},{"key":"e_1_3_2_1_10_1","volume-title":"RankVicuna: Zero-shot listwise doc umentreranking with open-source large language models. CoRR., abs\/2309.15088","author":"Pradeep R.","year":"2023","unstructured":"R. Pradeep, S. Sharifymoghaddam, and J. Lin. RankVicuna: Zero-shot listwise doc umentreranking with open-source large language models. CoRR., abs\/2309.15088, 2023."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-88711-6_12"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_2_1_14_1","volume-title":"Found in the middle: Permutation self-consistency improves listwise ranking in large language models. CoRR., abs\/2310.07712","author":"Tang R.","year":"2023","unstructured":"R. Tang, X. Zhang, X. Ma, J. Lin, and F. Ture. Found in the middle: Permutation self-consistency improves listwise ranking in large language models. CoRR., abs\/2310.07712, 2023."},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. NeurIPS Datasets and Benchmarks","author":"Thakur N.","year":"2021","unstructured":"N. Thakur, N. Reimers, A. R\u00fcckl\u00e9, A. Srivastava, and I. Gurevych. BEIR: A het erogeneous benchmark for zero-shot evaluation of information retrieval models. In Proc. NeurIPS Datasets and Benchmarks, 2021."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657707"},{"key":"e_1_3_2_1_17_1","volume-title":"A similarity measure for indefinite rankings. ACMTrans. Inf. Sys., 28(4):20.1-20.38","author":"Webber W.","year":"2010","unstructured":"W. Webber, A. Moffat, and J. Zobel. A similarity measure for indefinite rankings. ACMTrans. Inf. Sys., 28(4):20.1-20.38, 2010."},{"key":"e_1_3_2_1_18_1","first-page":"24824","volume":"35","author":"Wei J.","year":"2022","unstructured":"J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, and D. Zhou. Chain-of-thought prompting elicits reasoning in large language models. J. Adv. Neural. Inf. Process. Syst., 35:24824-24837, 2022.","journal-title":"Chain-of-thought prompting elicits reasoning in large language models. J. Adv. Neural. Inf. Process. Syst."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.31"},{"key":"e_1_3_2_1_20_1","first-page":"1483","volume-title":"Proc. SIGIR","year":"2021","unstructured":"S.ZhuangandG.Zuccon. TILDE:Term independent likelihood model for passage re-ranking. In Proc. SIGIR, pages 1483-1492, 2021."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72240-1_49"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657813"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:30:31Z","timestamp":1784136631000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":22,"alternative-id":["10.1145\/3805712.3809883","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809883","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}