{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T06:04:27Z","timestamp":1777615467502,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62441605, 62376243, 62037001, U20A20387"],"award-info":[{"award-number":["62441605, 62376243, 62037001, U20A20387"]}]},{"name":"the Starry Night Science Fund of Zhejiang University Shanghai Institute for Advanced Study","award":["SN-ZJU-SIAS-0010"],"award-info":[{"award-number":["SN-ZJU-SIAS-0010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671537","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"6003-6014","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Xinyu: An Efficient LLM-based System for Commentary Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5366-5027","authenticated-orcid":false,"given":"Yiquan","family":"Wu","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7129-0250","authenticated-orcid":false,"given":"Bo","family":"Tang","sequence":"additional","affiliation":[{"name":"Institute for Advanced Algorithms Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8211-2430","authenticated-orcid":false,"given":"Chenyang","family":"Xi","sequence":"additional","affiliation":[{"name":"Institute for Advanced Algorithms Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3109-7859","authenticated-orcid":false,"given":"Yu","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute for Advanced Algorithms Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2637-621X","authenticated-orcid":false,"given":"Pengyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7427-0024","authenticated-orcid":false,"given":"Yifei","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7024-9790","authenticated-orcid":false,"given":"Kun","family":"Kuang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7821-7196","authenticated-orcid":false,"given":"Haiying","family":"Deng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3771-0199","authenticated-orcid":false,"given":"Zhiyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Advanced Algorithms Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1456-2202","authenticated-orcid":false,"given":"Feiyu","family":"Xiong","sequence":"additional","affiliation":[{"name":"Institute for Advanced Algorithms Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9312-8430","authenticated-orcid":false,"given":"Jie","family":"Hu","sequence":"additional","affiliation":[{"name":"Research Institute of China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2662-3453","authenticated-orcid":false,"given":"Peng","family":"Cheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1322-9886","authenticated-orcid":false,"given":"Zhonghao","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5971-5368","authenticated-orcid":false,"given":"Yi","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9156-7590","authenticated-orcid":false,"given":"Yi","family":"Luo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Media Convergence Production Technology and Systems, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6747-9218","authenticated-orcid":false,"given":"Mingchuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Research Institute of China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"The opportunities and challenges of ChatGPT in education. Interactive Learning Environments","author":"Adeshola Ibrahim","year":"2023","unstructured":"Ibrahim Adeshola and Adeola Praise Adepoju. 2023. The opportunities and challenges of ChatGPT in education. Interactive Learning Environments (2023), 1--14."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.76"},{"key":"e_1_3_2_1_4_1","volume-title":"John S Kuo, and Kuan-Pin Su.","author":"Cheng Szu-Wei","year":"2023","unstructured":"Szu-Wei Cheng, Chung-Wen Chang, Wan-Jung Chang, Hao-Wei Wang, Chih-Sung Liang, Taishiro Kishimoto, Jane Pei-Chen Chang, John S Kuo, and Kuan-Pin Su. 2023. The now and future of ChatGPT and GPT in psychiatry. Psychiatry and clinical neurosciences, Vol. 77, 11 (2023), 592--596."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-00296-0"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2306.16092"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.13160"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Luyu Gao Xueguang Ma Jimmy Lin and Jamie Callan. 2022. Precise Zero-Shot Dense Retrieval without Relevance Labels. arxiv: 2212.10496 [cs.IR]","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.10997"},{"key":"e_1_3_2_1_10_1","volume-title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models. arxiv: 2208.03299 [cs.CL]","author":"Izacard Gautier","year":"2022","unstructured":"Gautier Izacard, Patrick Lewis, Maria Lomeli, Lucas Hosseini, Fabio Petroni, Timo Schick, Jane Dwivedi-Yu, Armand Joulin, Sebastian Riedel, and Edouard Grave. 2022. Atlas: Few-shot Learning with Retrieval Augmented Language Models. arxiv: 2208.03299 [cs.CL]"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.12871"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2303.14070"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.15461"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591731"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.14283"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3587102.3588827"},{"key":"e_1_3_2_1_18_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/b1efde53be364a73914f58805a001731-Abstract-Conference.html"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Zhihong Shao Yeyun Gong Yelong Shen Minlie Huang Nan Duan and Weizhu Chen. 2023. Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy. arxiv: 2305.15294 [cs.CL]","DOI":"10.18653\/v1\/2023.findings-emnlp.620"},{"key":"e_1_3_2_1_21_1","volume-title":"Mask the correct tokens: An embarrassingly simple approach for error correction. arXiv preprint arXiv:2211.13252","author":"Shen Kai","year":"2022","unstructured":"Kai Shen, Yichong Leng, Xu Tan, Siliang Tang, Yuan Zhang, Wenjie Liu, and Edward Lin. 2022. Mask the correct tokens: An embarrassingly simple approach for error correction. arXiv preprint arXiv:2211.13252 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"REPLUG: Retrieval-Augmented Black-Box Language Models. arxiv: 2301.12652 [cs.CL]","author":"Shi Weijia","year":"2023","unstructured":"Weijia Shi, Sewon Min, Michihiro Yasunaga, Minjoon Seo, Rich James, Mike Lewis, Luke Zettlemoyer, and Wen tau Yih. 2023. REPLUG: Retrieval-Augmented Black-Box Language Models. arxiv: 2301.12652 [cs.CL]"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Karan Singhal Shekoofeh Azizi Tao Tu S. Sara Mahdavi Jason Wei Hyung Won Chung Nathan Scales Ajay Kumar Tanwani Heather Cole-Lewis Stephen Pfohl Perry Payne Martin Seneviratne Paul Gamble Chris Kelly Nathaneal Sch\u00e4rli Aakanksha Chowdhery Philip Andrew Mansfield Blaise Ag\u00fcera y Arcas Dale R. Webster Gregory S. Corrado Yossi Matias Katherine Chou Juraj Gottweis Nenad Tomasev Yun Liu Alvin Rajkomar Joelle K. Barral Christopher Semturs Alan Karthikesalingam and Vivek Natarajan. 2022. Large Language Models Encode Clinical Knowledge. CoRR Vol. abs\/2212.13138 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2212.13138 [arXiv]2212.13138","DOI":"10.48550\/ARXIV.2212.13138"},{"key":"e_1_3_2_1_24_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). https:\/\/doi.org\/10.48550\/ARXIV.2305.09617 [arXiv]2305.09617","DOI":"10.48550\/ARXIV.2305.09617"},{"key":"e_1_3_2_1_25_1","volume-title":"Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation. CoRR","author":"Sun Yu","year":"2021","unstructured":"Yu Sun, Shuohuan Wang, Shikun Feng, Siyu Ding, Chao Pang, Junyuan Shang, Jiaxiang Liu, Xuyi Chen, Yanbin Zhao, Yuxiang Lu, Weixin Liu, Zhihua Wu, Weibao Gong, Jianzhong Liang, Zhizhou Shang, Peng Sun, Wei Liu, Xuan Ouyang, Dianhai Yu, Hao Tian, Hua Wu, and Haifeng Wang. 2021. ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation. CoRR, Vol. abs\/2107.02137 (2021). [arXiv]2107.02137 https:\/\/arxiv.org\/abs\/2107.02137"},{"key":"e_1_3_2_1_26_1","unstructured":"InternLM Team. 2023. InternLM: A Multilingual Language Model with Progressively Enhanced Capabilities. https:\/\/github.com\/InternLM\/InternLM."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.13971"},{"key":"e_1_3_2_1_28_1","unstructured":"VoyageAI. 2023. VoyageAI. Voyage's embedding models. https:\/\/docs.voyageai.com\/embeddings\/."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Liang Wang Nan Yang and Furu Wei. 2023. Query2doc: Query Expansion with Large Language Models. arxiv: 2303.07678 [cs.IR]","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.56"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.797"},{"key":"e_1_3_2_1_32_1","volume-title":"Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration. arXiv preprint arXiv:2310.09241","author":"Wu Yiquan","year":"2023","unstructured":"Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, and Kun Kuang. 2023. Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration. arXiv preprint arXiv:2310.09241 (2023)."},{"key":"e_1_3_2_1_33_1","unstructured":"Shitao Xiao Zheng Liu Peitian Zhang and Niklas Muennighoff. 2023. C-Pack: Packaged Resources To Advance General Chinese Embedding. arxiv: 2309.07597 [cs.CL]"},{"key":"e_1_3_2_1_34_1","volume-title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation. arxiv: 2310.04408 [cs.CL]","author":"Xu Fangyuan","year":"2023","unstructured":"Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2023. RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation. arxiv: 2310.04408 [cs.CL]"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.10305"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.08173"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.11325"},{"key":"e_1_3_2_1_38_1","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Zeng Aohan","year":"2023","unstructured":"Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yufei Xue, Jidong Zhai, Wenguang Chen, Zhiyuan Liu, Peng Zhang, Yuxiao Dong, and Jie Tang. 2023. GLM-130B: An Open Bilingual Pre-trained Model. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/pdf?id=-Aw0rrrPUF"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Rongzhi Zhang Jiaming Shen Tianqi Liu Haorui Wang Zhen Qin Feng Han Jialu Liu Simon Baumgartner Michael Bendersky and Chao Zhang. 2024. PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs. arxiv: 2406.02886 [cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.923"},{"key":"e_1_3_2_1_40_1","unstructured":"Xujiang Zhao Jiaying Lu Chengyuan Deng Can Zheng Junxiang Wang Tanmoy Chowdhury Li Yun Hejie Cui Zhang Xuchao Tianjiao Zhao et al. 2023. Domain specialization as the key to make large language models disruptive: A comprehensive survey. arXiv preprint arXiv:2305.18703 (2023)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.11206"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20503-3_23"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671537","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:19Z","timestamp":1750291459000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671537"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":40,"alternative-id":["10.1145\/3637528.3671537","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671537","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}