{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:23Z","timestamp":1784138723366,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809945","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"4181-4186","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Route Queries to Heads for Attention-based Re-ranking with Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0313-5089","authenticated-orcid":false,"given":"Yuxing","family":"Tian","sequence":"first","affiliation":[{"name":"Universit\u00e9 de Montr\u00e9al, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0838-6994","authenticated-orcid":false,"given":"Fengran","family":"Mo","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Montr\u00e9al, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2939-1936","authenticated-orcid":false,"given":"Zhiqi","family":"Huang","sequence":"additional","affiliation":[{"name":"CapitalOne, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2000-7891","authenticated-orcid":false,"given":"Weixu","family":"Zhang","sequence":"additional","affiliation":[{"name":"McGill University, Montreal, QC, Canada and Mila - Quebec Artificial Intelligence Institute, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1556-3335","authenticated-orcid":false,"given":"Jian-Yun","family":"Nie","sequence":"additional","affiliation":[{"name":"Universit\u00e9 de Montr\u00e9al, Montreal, QC, Canada"}],"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":"10.1007\/978-3-319-30671-1_58"},{"key":"e_1_3_2_1_2_1","volume-title":"Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers. In The Thirteenth International Conference on Learning Representations.","author":"Chen Shijie","year":"2025","unstructured":"Shijie Chen, Bernal Jimenez Gutierrez, and Yu Su. 2025. Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","volume-title":"Extending context window of large language models via positional interpolation. arXiv preprint arXiv:2306.15595","author":"Chen Shouyuan","year":"2023","unstructured":"Shouyuan Chen, Sherman Wong, Liangjian Chen, and Yuandong Tian. 2023. Extending context window of large language models via positional interpolation. arXiv preprint arXiv:2306.15595 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Specter: Document-level representation learning using citation-informed transformers. arXiv preprint arXiv:2004.07180","author":"Cohan Arman","year":"2020","unstructured":"Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel S Weld. 2020. Specter: Document-level representation learning using citation-informed transformers. arXiv preprint arXiv:2004.07180 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"Climate-fever: A dataset for verification of real-world climate claims. arXiv preprint arXiv:2012.00614","author":"Diggelmann Thomas","year":"2020","unstructured":"Thomas Diggelmann, Jordan Boyd-Graber, Jannis Bulian, Massimiliano Ciaramita, and Markus Leippold. 2020. Climate-fever: A dataset for verification of real-world climate claims. arXiv preprint arXiv:2012.00614 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Data engineering for scaling language models to 128k context. arXiv preprint arXiv:2402.10171","author":"Fu Yao","year":"2024","unstructured":"Yao Fu, Rameswar Panda, Xinyao Niu, Xiang Yue, Hannaneh Hajishirzi, Yoon Kim, and Hao Peng. 2024. Data engineering for scaling language models to 128k context. arXiv preprint arXiv:2402.10171 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yixin Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, Vol. 2, 1 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080751"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NTEz-6wysdb","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard and Edouard Grave. 2021. Distilling Knowledge from Reader to Retriever for Question Answering. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=NTEz-6wysdb"},{"key":"e_1_3_2_1_10_1","unstructured":"Vitor Jeronymo Mauricio Nascimento Roberto Lotufo and Rodrigo Nogueira. 2022. mRobust04: A Multilingual Version of the TREC Robust 2004 Benchmark. arXiv:2209.13738 [cs.CL] https:\/\/arxiv.org\/abs\/2209.13738"},{"key":"e_1_3_2_1_11_1","volume-title":"Llm maybe longlm: Self-extend llm context window without tuning. arXiv preprint arXiv:2401.01325","author":"Jin Hongye","year":"2024","unstructured":"Hongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang, Zirui Liu, Chia-Yuan Chang, Huiyuan Chen, and Xia Hu. 2024. Llm maybe longlm: Self-extend llm context window without tuning. arXiv preprint arXiv:2401.01325 (2024)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_14_1","volume-title":"Natural Questions: a Benchmark for Question Answering Research. Transactions of the Association of Computational Linguistics","author":"Kwiatkowski Tom","year":"2019","unstructured":"Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Matthew Kelcey, Jacob Devlin, Kenton Lee, Kristina N. Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov. 2019. Natural Questions: a Benchmark for Question Answering Research. Transactions of the Association of Computational Linguistics (2019)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.695"},{"key":"e_1_3_2_1_16_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, et al., 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, Vol. 33 (2020), 9459-9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar et al. 2022. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110 (2022)."},{"key":"e_1_3_2_1_18_1","volume-title":"Zero-shot listwise document reranking with a large language model. arXiv preprint arXiv:2305.02156","author":"Ma Xueguang","year":"2023","unstructured":"Xueguang Ma, Xinyu Zhang, Ronak Pradeep, and Jimmy Lin. 2023. Zero-shot listwise document reranking with a large language model. arXiv preprint arXiv:2305.02156 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3192301"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657864"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3736402"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3805712.3808557"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729915"},{"key":"e_1_3_2_1_24_1","volume-title":"Are sixteen heads really better than one? Advances in neural information processing systems","author":"Michel Paul","year":"2019","unstructured":"Paul Michel, Omer Levy, and Graham Neubig. 2019. Are sixteen heads really better than one? Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.344"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3759453"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.274"},{"key":"e_1_3_2_1_28_1","volume-title":"Zheyuan Liu, Chao Zhang, Tetsuya Sakai, and Jian-Yun Nie.","author":"Mo Fengran","year":"2026","unstructured":"Fengran Mo, Zhan Su, Yuchen Hui, Jinghan Zhang, Jia Ao Sun, Zheyuan Liu, Chao Zhang, Tetsuya Sakai, and Jian-Yun Nie. 2026. Opendecoder: Open large language model decoding to incorporate document quality in rag. arXiv preprint arXiv:2601.09028 (2026)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.669"},{"key":"e_1_3_2_1_30_1","volume-title":"Document ranking with a pretrained sequence-to-sequence model. arXiv preprint arXiv:2003.06713","author":"Nogueira Rodrigo","year":"2020","unstructured":"Rodrigo Nogueira, Zhiying Jiang, and Jimmy Lin. 2020. Document ranking with a pretrained sequence-to-sequence model. arXiv preprint arXiv:2003.06713 (2020)."},{"key":"e_1_3_2_1_31_1","volume-title":"Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424","author":"Nogueira Rodrigo","year":"2019","unstructured":"Rodrigo Nogueira, Wei Yang, Kyunghyun Cho, and Jimmy Lin. 2019. Multi-stage document ranking with BERT. arXiv preprint arXiv:1910.14424 (2019)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.249"},{"key":"e_1_3_2_1_35_1","volume-title":"BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ykuc5q381b","author":"Howard Yen Hongjin SU","year":"2025","unstructured":"Hongjin SU, Howard Yen, Mengzhou Xia, Weijia Shi, Niklas Muennighoff, Han yu Wang, Liu Haisu, Quan Shi, Zachary S Siegel, Michael Tang, Ruoxi Sun, Jinsung Yoon, Sercan O Arik, Danqi Chen, and Tao Yu. 2025. BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=ykuc5q381b"},{"key":"e_1_3_2_1_36_1","unstructured":"Zhan Su Fengran Mo Jinghan Zhang Yuchen Hui Jiaao Sun and Jian yun Nie. 2026. Parametric Retrieval-Augmented Generation using Latent Routing of LoRA Adapters. arXiv:2511.17044 [cs.IR] https:\/\/arxiv.org\/abs\/2511.17044"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.923"},{"key":"e_1_3_2_1_38_1","unstructured":"Nandan Thakur Nils Reimers Andreas R\u00fcckl\u00e9 Abhishek Srivastava and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2). https:\/\/openreview.net\/forum?id=wCu6T5xFjeJ"},{"key":"e_1_3_2_1_39_1","volume-title":"FEVER: a large-scale dataset for fact extraction and VERification. arXiv preprint arXiv:1803.05355","author":"Thorne James","year":"2018","unstructured":"James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and VERification. arXiv preprint arXiv:1803.05355 (2018)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.findings-eacl.66"},{"key":"e_1_3_2_1_41_1","unstructured":"Linh Tran Yulong Li Radu Florian and Wei Sun. 2025. Contrastive Retrieval Heads Improve Attention-Based Re-Ranking. arXiv:2510.02219 [cs.IR] https:\/\/arxiv.org\/abs\/2510.02219"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"e_1_3_2_1_43_1","first-page":"1","volume-title":"ACM SIGIR Forum","volume":"54","author":"Voorhees Ellen","year":"2021","unstructured":"Ellen Voorhees, Tasmeer Alam, Steven Bedrick, Dina Demner-Fushman, William R Hersh, Kyle Lo, Kirk Roberts, Ian Soboroff, and Lucy Lu Wang. 2021. TREC-COVID: constructing a pandemic information retrieval test collection. In ACM SIGIR Forum, Vol. 54. ACM New York, NY, USA, 1-12."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.609"},{"key":"e_1_3_2_1_45_1","volume-title":"Rosie Guo, Fengran Mo, et al.","author":"Wang Yan","year":"2026","unstructured":"Yan Wang, Yi Han, Lingfei Qian, Yueru He, Xueqing Peng, Dongji Feng, Zhuohan Xie, Vincent Jim Zhang, Rosie Guo, Fengran Mo, et al., 2026. Conv-FinRe: A Conversational and Longitudinal Benchmark for Utility-Grounded Financial Recommendation. arXiv preprint arXiv:2602.16990 (2026)."},{"key":"e_1_3_2_1_46_1","volume-title":"Retrieval Head Mechanistically Explains Long-Context Factuality. In The Thirteenth International Conference on Learning Representations.","author":"Wu Wenhao","year":"2025","unstructured":"Wenhao Wu, Yizhong Wang, Guangxuan Xiao, Hao Peng, and Yao Fu. 2025. Retrieval Head Mechanistically Explains Long-Context Factuality. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"e_1_3_2_1_48_1","volume-title":"A survey of model architectures in information retrieval. arXiv preprint arXiv:2502.14822","author":"Xu Zhichao","year":"2025","unstructured":"Zhichao Xu, Fengran Mo, Zhiqi Huang, Crystina Zhang, Puxuan Yu, Bei Wang, Jimmy Lin, and Vivek Srikumar. 2025. A survey of model architectures in information retrieval. arXiv preprint arXiv:2502.14822 (2025)."},{"key":"e_1_3_2_1_49_1","volume-title":"Blind spot navigation in llm reasoning with thought space explorer. arXiv preprint arXiv:2410.24155","author":"Zhang Jinghan","year":"2024","unstructured":"Jinghan Zhang, Fengran Mo, Xiting Wang, and Kunpeng Liu. 2024. Blind spot navigation in llm reasoning with thought space explorer. arXiv preprint arXiv:2410.24155 (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"Ruimin Dai, Xiaoyan Han, Yanjie Fu, Dakuo Wang, and Kunpeng Liu. 2026 a. StaRPO: Stability-Augmented Reinforcement Policy Optimization. arXiv preprint arXiv:2604.08905","author":"Zhang Jinghan","year":"2026","unstructured":"Jinghan Zhang, Fengran Mo, Tharindu Cyril Weerasooriya, Ruimin Dai, Xiaoyan Han, Yanjie Fu, Dakuo Wang, and Kunpeng Liu. 2026 a. StaRPO: Stability-Augmented Reinforcement Policy Optimization. arXiv preprint arXiv:2604.08905 (2026)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i25.34876"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Weixu Zhang Fanghua Ye Qiang Gao Jian Li Haolun Wu Yuxing Tian Sijing Duan Nan Du Xiaolong Li and Xue Liu. 2026 b. Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding. arXiv:2604.22335 [cs.CL] https:\/\/arxiv.org\/abs\/2604.22335","DOI":"10.18653\/v1\/2026.findings-acl.2121"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1214"},{"key":"e_1_3_2_1_54_1","unstructured":"Weixu Zhang Ye Yuan Changjiang Han Yuxing Tian Zipeng Sun Linfeng Du Jikun Kang Hong Kang Xue Liu and Haolun Wu. 2026 c. Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization. arXiv:2604.22345 [cs.CL] https:\/\/arxiv.org\/abs\/2604.22345"}],"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":"2026-07-15T17:15:19Z","timestamp":1784135719000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":54,"alternative-id":["10.1145\/3805712.3809945","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809945","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"}}]}}