{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:51:20Z","timestamp":1783788680705,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657824","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1995-2005","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["MTMS: Multi-teacher Multi-stage Knowledge Distillation for Reasoning-Based Machine Reading Comprehension"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0907-3620","authenticated-orcid":false,"given":"Zhuo","family":"Zhao","sequence":"first","affiliation":[{"name":"Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, China, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0837-3285","authenticated-orcid":false,"given":"Zhiwen","family":"Xie","sequence":"additional","affiliation":[{"name":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning & School of Computer, Central China Normal University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7675-6619","authenticated-orcid":false,"given":"Guangyou","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning & School of Computer, Central China Normal University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1292-1491","authenticated-orcid":false,"given":"Jimmy Xiangji","family":"Huang","sequence":"additional","affiliation":[{"name":"Information Retrieval and Knowledge Management Research Lab, York University, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6243"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19888"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3578741.3578816"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.109"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 1467--1479","author":"Chen Jialin","year":"2022","unstructured":"Jialin Chen, Zhuosheng Zhang, and Hai Zhao. 2022. Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 1467--1479. https:\/\/aclanthology.org\/2022.coling-1.126"},{"key":"e_1_3_2_1_7_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma et al. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462978"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00921"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Learning Representations.","author":"He Pengcheng","year":"2021","unstructured":"Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. 2021. DeBERTa: Decoding-enhanced bert with disentangled attention. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"e_1_3_2_1_13_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_14_1","volume-title":"Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISOCC56007.2022.10031412"},{"key":"e_1_3_2_1_16_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18--1232"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.467"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109331"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.276"},{"key":"e_1_3_2_1_22_1","volume-title":"Chen","author":"Jiao Fangkai","year":"2023","unstructured":"Fangkai Jiao, Zhiyang Teng, Shafiq Joty, Bosheng Ding, Aixin Sun, Zhengyuan Liu, and Nancy F. Chen. 2023. LogicLLM: Exploring Self-supervised Logic-enhanced Training for Large Language Models. arXiv preprint arXiv:2305.13718 (2023). arxiv: 2305.13718 [cs.CL]"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR).","author":"Kingma Diederick P","year":"2015","unstructured":"Diederick P Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.494"},{"key":"e_1_3_2_1_25_1","volume-title":"2023 c. Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4. arXiv preprint arXiv:2304.03439","author":"Liu Hanmeng","year":"2023","unstructured":"Hanmeng Liu, Ruoxi Ning, Zhiyang Teng, Jian Liu, Qiji Zhou, and Yue Zhang. 2023 c. Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4. arXiv preprint arXiv:2304.03439 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 3622--3628","author":"Liu Jian","year":"2021","unstructured":"Jian Liu, Leyang Cui, Hanmeng Liu, Dandan Huang, Yile Wang, and Yue Zhang. 2021. LogiQA: a challenge dataset for machine reading comprehension with logical reasoning. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 3622--3628."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103145"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/app9183698"},{"key":"e_1_3_2_1_29_1","volume-title":"2023 a. Summary of chatgpt-related research and perspective towards the future of large language models. Meta-Radiology","author":"Liu Yiheng","year":"2023","unstructured":"Yiheng Liu, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He, Antong Li, Mengshen He, Zhengliang Liu, et al. 2023 a. Summary of chatgpt-related research and perspective towards the future of large language models. Meta-Radiology (2023), 100017."},{"key":"e_1_3_2_1_30_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. 2019a. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR , Vol. abs\/1907.11692 (2019). arxiv: 1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.5753\/stil.2021.17801"},{"key":"e_1_3_2_1_32_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_33_1","volume-title":"Fact-driven logical reasoning. arXiv preprint arXiv:2105.10334","author":"Ouyang Siru","year":"2021","unstructured":"Siru Ouyang, Zhuosheng Zhang, and Hai Zhao. 2021. Fact-driven logical reasoning. arXiv preprint arXiv:2105.10334 (2021)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bea-1.26"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i10.7223"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.347"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612162"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.479"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/IALP61005.2023.10337099"},{"key":"e_1_3_2_1_41_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_42_1","volume-title":"Graph Attention Networks. In International Conference on Learning Representations.","author":"Petar","year":"2018","unstructured":"Petar Veli?kovi?, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Li\u00f2, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","unstructured":"Chen Wang Jiang Zhong Qizhu Dai Yafei Qi Rongzhen Li Qin Lei Bin Fang and Xue Li. 2023. PRRD: Pixel-Region Relation Distillation For Efficient Semantic Segmentation. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 1--5. https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10094967","DOI":"10.1109\/ICASSP49357.2023.10094967"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.127"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the 20th Chinese National Conference on Computational Linguistics. 1024--1036","author":"Xiaoyan Yu","year":"2021","unstructured":"Yu Xiaoyan, Liu Qingbin, He Shizhu, Liu Kang, Liu Shengping, Zhao Jun, and Zhou Yongbin. 2021. Multi-Strategy Knowledge Distillation Based Teacher-Student Framework for Machine Reading Comprehension. In Proceedings of the 20th Chinese National Conference on Computational Linguistics. 1024--1036. https:\/\/aclanthology.org\/2021.ccl-1.91"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532016"},{"key":"e_1_3_2_1_49_1","volume-title":"Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text. arXiv preprint arXiv:2301.02983","author":"Xu Fangzhi","year":"2023","unstructured":"Fangzhi Xu, Jun Liu, Qika Lin, Tianzhe Zhao, Jian Zhang, and Lingling Zhang. 2023. Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text. arXiv preprint arXiv:2301.02983 (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning. In International Conference on Learning Representations.","author":"Yu Weihao","year":"2020","unstructured":"Weihao Yu, Zihang Jiang, Yanfei Dong, and Jiashi Feng. 2020. ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298809"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658673"},{"key":"e_1_3_2_1_53_1","volume-title":"Large Language Models Are Not Robust Multiple Choice Selectors. arXiv preprint arXiv:2309.03882","author":"Zheng Chujie","year":"2023","unstructured":"Chujie Zheng, Hao Zhou, Fandong Meng, Jie Zhou, and Minlie Huang. 2023. Large Language Models Are Not Robust Multiple Choice Selectors. arXiv preprint arXiv:2309.03882 (2023). arxiv: 2309.03882 [cs.CL]"},{"key":"e_1_3_2_1_54_1","volume-title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Zheng Lianmin","year":"2022","unstructured":"Lianmin Zheng, Zhuohan Li, Hao Zhang, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P. Xing, Joseph E. Gonzalez, and Ion Stoica. 2022. Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA, 559--578. https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/zheng-lianmin"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657824","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:38:52Z","timestamp":1755841132000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657824"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":54,"alternative-id":["10.1145\/3626772.3657824","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657824","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}