{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:40:01Z","timestamp":1755866401888,"version":"3.44.0"},"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":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730243","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:25:28Z","timestamp":1752456328000},"page":"2956-2961","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning for Effective Few-Shot Ranking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8518-7514","authenticated-orcid":false,"given":"Shiva","family":"Soleimany","sequence":"first","affiliation":[{"name":"University of Toronto, Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1630-3938","authenticated-orcid":false,"given":"Sajad","family":"Ebrahimi","sequence":"additional","affiliation":[{"name":"University of Guelph, Toronto, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1467-1659","authenticated-orcid":false,"given":"Shirin","family":"Seyedsalehi","sequence":"additional","affiliation":[{"name":"Toronto Metropolitan University, Toronto, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2102-9190","authenticated-orcid":false,"given":"Fattane","family":"Zarrinkalam","sequence":"additional","affiliation":[{"name":"University of Guelph, Guelph, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5148-6237","authenticated-orcid":false,"given":"Ebrahim","family":"Bagheri","sequence":"additional","affiliation":[{"name":"University of Toronto, Toronto, ON, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615270"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.IPM.2018.04.007"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56066-8_5"},{"key":"e_1_3_2_1_4_1","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=r1xMH1BtvB"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-88714-7_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018692"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3209979"},{"key":"e_1_3_2_1_8_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"He Pengcheng","year":"2023","unstructured":"Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2023. DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=sE7-XhLxHA"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679912"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531786"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219846"},{"key":"e_1_3_2_1_12_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=79eWvkLjib","author":"Jeen Scott","year":"2024","unstructured":"Scott Jeen, Tom Bewley, and Jonathan Cullen. 2024. Zero-Shot Reinforcement Learning from Low Quality Data. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=79eWvkLjib"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119015"},{"key":"e_1_3_2_1_14_1","volume-title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In 8th International Conference on Learning Representations, ICLR 2020","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=H1eA7AEtvS"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"e_1_3_2_1_16_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR, Vol. abs\/1907.11692 (2019). showeprint[arXiv]1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052579"},{"key":"e_1_3_2_1_18_1","volume-title":"Riedmiller","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin A. Riedmiller. 2013. Playing Atari with Deep Reinforcement Learning. CoRR, Vol. abs\/1312.5602 (2013). [arXiv]1312.5602 http:\/\/arxiv.org\/abs\/1312.5602"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/NATURE14236"},{"key":"e_1_3_2_1_20_1","volume-title":"Bridging the Gap Between Value and Policy Based Reinforcement Learning. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Nachum Ofir","year":"2017","unstructured":"Ofir Nachum, Mohammad Norouzi, Kelvin Xu, and Dale Schuurmans. 2017. Bridging the Gap Between Value and Policy Based Reinforcement Learning. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 2775-2785. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/facf9f743b083008a894eee7baa16469-Abstract.html"},{"key":"e_1_3_2_1_21_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016) Barcelona Spain December 9 2016 (CEUR Workshop Proceedings Vol. 1773) Tarek Richard Besold Antoine Bordes Artur S. d'Avila Garcez and Greg Wayne (Eds.). CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"key":"e_1_3_2_1_22_1","article-title":"A Survey of Temporal Credit Assignment in Deep Reinforcement","volume":"2024","author":"Pignatelli Eduardo","year":"2024","unstructured":"Eduardo Pignatelli, Johan Ferret, Matthieu Geist, Thomas Mesnard, Hado van Hasselt, and Laura Toni. 2024. A Survey of Temporal Credit Assignment in Deep Reinforcement Learning. Trans. Mach. Learn. Res., Vol. 2024 (2024). https:\/\/openreview.net\/forum?id=bNtr6SLgZf","journal-title":"Learning. Trans. Mach. Learn. Res."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316887"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2020.EMNLP-MAIN.365"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401280"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_27_1","volume-title":"Experience Replay for Continual Learning. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019","author":"Rolnick David","year":"2019","unstructured":"David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy P. Lillicrap, and Gregory Wayne. 2019. Experience Replay for Continual Learning. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alch\u00e9-Buc, Emily B. Fox, and Roman Garnett (Eds.). 348-358. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/fa7cdfad1a5aaf8370ebeda47a1ff1c3-Abstract.html"},{"key":"e_1_3_2_1_28_1","volume-title":"Data-Efficient Reinforcement Learning with Momentum Predictive Representations. CoRR","author":"Schwarzer Max","year":"2020","unstructured":"Max Schwarzer, Ankesh Anand, Rishab Goel, R. Devon Hjelm, Aaron C. Courville, and Philip Bachman. 2020. Data-Efficient Reinforcement Learning with Momentum Predictive Representations. CoRR, Vol. abs\/2007.05929 (2020). [arXiv]2007.05929 https:\/\/arxiv.org\/abs\/2007.05929"},{"key":"e_1_3_2_1_29_1","volume-title":"Courville","author":"Schwarzer Max","year":"2021","unstructured":"Max Schwarzer, Nitarshan Rajkumar, Michael Noukhovitch, Ankesh Anand, Laurent Charlin, R. Devon Hjelm, Philip Bachman, and Aaron C. Courville. 2021. Pretraining Representations for Data-Efficient Reinforcement Learning. CoRR, Vol. abs\/2106.04799 (2021). [arXiv]2106.04799 https:\/\/arxiv.org\/abs\/2106.04799"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-024-06664-2"},{"key":"e_1_3_2_1_31_1","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Shi Guangyuan","year":"2021","unstructured":"Guangyuan Shi, Jiaxin Chen, Wenlong Zhang, Li-Ming Zhan, and Xiao-Ming Wu. 2021. Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 6747-6761. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/357cfba15668cc2e1e73111e09d54383-Abstract.html"},{"key":"e_1_3_2_1_32_1","volume-title":"Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model. In Findings of the Association for Computational Linguistics: EMNLP 2024","author":"Sinhababu Nilanjan","year":"2024","unstructured":"Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly, Debasis Samanta, and Pabitra Mitra. 2024. Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, USA, November 12-16, 2024, Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (Eds.). Association for Computational Linguistics, 12363-12377. https:\/\/aclanthology.org\/2024.findings-emnlp.720"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-46133-1_2"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","unstructured":"Si Sun Yingzhuo Qian Zhenghao Liu Chenyan Xiong Kaitao Zhang Jie Bao Zhiyuan Liu and Paul Bennett. 2021. Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing ACL\/IJCNLP 2021 (Volume 1: Long Papers) Virtual Event August 1-6 2021 Chengqing Zong Fei Xia Wenjie Li and Roberto Navigli (Eds.). Association for Computational Linguistics 5030-5043. doi:10.18653\/V1\/2021.ACL-LONG.390","DOI":"10.18653\/V1\/2021.ACL-LONG.390"},{"key":"e_1_3_2_1_35_1","volume-title":"Barto","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction (second ed.). The MIT Press. http:\/\/incompleteideas.net\/book\/the-book-2nd.html"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1162\/089892999563184"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1183614.1183698"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28238-6_57"},{"key":"e_1_3_2_1_39_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Wang Ziyu","year":"2017","unstructured":"Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, R\u00e9mi Munos, Koray Kavukcuoglu, and Nando de Freitas. 2017. Sample Efficient Actor-Critic with Experience Replay. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=HyM25Mqel"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080685"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080775"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462812"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3234944.3234977"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609529"},{"key":"e_1_3_2_1_45_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Zhang Zeyu","year":"2023","unstructured":"Zeyu Zhang, Yi Su, Hui Yuan, Yiran Wu, Rishab Balasubramanian, Qingyun Wu, Huazheng Wang, and Mengdi Wang. 2023. Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/3f1b6e97a5eb3b10e6b0c99b022988eb-Abstract-Conference.html"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330668"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:20:01Z","timestamp":1755865201000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730243"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":46,"alternative-id":["10.1145\/3726302.3730243","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730243","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}