{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T23:03:13Z","timestamp":1778194993886,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":78,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN- 2021-02575"],"award-info":[{"award-number":["RGPIN- 2021-02575"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,12]]},"DOI":"10.1145\/3597503.3639194","type":"proceedings-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T16:43:26Z","timestamp":1712940206000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["ChatGPT Incorrectness Detection in Software Reviews"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3323-4917","authenticated-orcid":false,"given":"Minaoar Hossain","family":"Tanzil","sequence":"first","affiliation":[{"name":"University of Calgary, Calgary, Alberta, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8138-1105","authenticated-orcid":false,"given":"Junaed Younus","family":"Khan","sequence":"additional","affiliation":[{"name":"University of Calgary, Calgary, Alberta, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1376-095X","authenticated-orcid":false,"given":"Gias","family":"Uddin","sequence":"additional","affiliation":[{"name":"York University, Toronto, Ontario, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3559555"},{"key":"e_1_3_2_1_3_1","unstructured":"Open AI. 2023. GPT-4 --- openai.com. https:\/\/openai.com\/research\/gpt-4. [Accessed 01-08-2023]."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Rahul Aralikatte Shashi Narayan Joshua Maynez Sascha Rothe and Ryan McDonald. 2021. Focus Attention: Promoting Faithfulness and Diversity in Summarization. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics Online 6078--6095. 10.18653\/v1\/2021.acl-long.474","DOI":"10.18653\/v1\/2021.acl-long.474"},{"key":"e_1_3_2_1_5_1","volume-title":"The internal state of an llm knows when its lying. arXiv preprint arXiv:2304.13734","author":"Azaria Amos","year":"2023","unstructured":"Amos Azaria and Tom Mitchell. 2023. The internal state of an llm knows when its lying. arXiv preprint arXiv:2304.13734 (2023)."},{"key":"e_1_3_2_1_6_1","first-page":"38176","article-title":"Fine-tuning language models to find agreement among humans with diverse preferences","volume":"35","author":"Bakker Michiel","year":"2022","unstructured":"Michiel Bakker, Martin Chadwick, Hannah Sheahan, Michael Tessler, Lucy Campbell-Gillingham, Jan Balaguer, Nat McAleese, Amelia Glaese, John Aslanides, Matt Botvinick, et al. 2022. Fine-tuning language models to find agreement among humans with diverse preferences. Advances in Neural Information Processing Systems 35 (2022), 38176--38189.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Yejin Bang Samuel Cahyawijaya Nayeon Lee Wenliang Dai Dan Su Bryan Wilie Holy Lovenia Ziwei Ji Tiezheng Yu Willy Chung et al. 2023. A multitask multilingual multimodal evaluation of chatgpt on reasoning hallucination and interactivity. arXiv preprint arXiv:2302.04023 (2023).","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"e_1_3_2_1_8_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 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5602"},{"key":"e_1_3_2_1_10_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE51524.2021.9678670"},{"key":"e_1_3_2_1_12_1","volume-title":"BoolQ: Exploring the surprising difficulty of natural yes\/no questions. arXiv preprint arXiv:1905.10044","author":"Clark Christopher","year":"2019","unstructured":"Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. 2019. BoolQ: Exploring the surprising difficulty of natural yes\/no questions. arXiv preprint arXiv:1905.10044 (2019)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.156"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the 14th International Conference on Predictive Models and Data Analytics in Software Engineering. Association for Computing Machinery","author":"Fernando","unstructured":"Fernando L\u00f3pez de la Mora and Sarah Nadi. 2018. An empirical study of metric-based comparisons of software libraries. In Proceedings of the 14th International Conference on Predictive Models and Data Analytics in Software Engineering. Association for Computing Machinery, New York, NY, USA, 22--31."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183399.3183418"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1177\/0093854818758808"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1483"},{"key":"e_1_3_2_1_18_1","volume-title":"Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495","author":"Dhuliawala Shehzaad","year":"2023","unstructured":"Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason Weston. 2023. Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.168"},{"key":"e_1_3_2_1_20_1","volume-title":"From Hero to Z\\'eroe: A Benchmark of Low-Level Adversarial Attacks. arXiv preprint arXiv:2010.05648","author":"Eger Steffen","year":"2020","unstructured":"Steffen Eger and Yannik Benz. 2020. From Hero to Z\\'eroe: A Benchmark of Low-Level Adversarial Attacks. arXiv preprint arXiv:2010.05648 (2020)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417922"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00410"},{"key":"e_1_3_2_1_23_1","volume-title":"Trapping LLM Hallucinations Using Tagged Context Prompts. arXiv preprint arXiv:2306.06085","author":"Feldman Philip","year":"2023","unstructured":"Philip Feldman, James R Foulds, and Shimei Pan. 2023. Trapping LLM Hallucinations Using Tagged Context Prompts. arXiv preprint arXiv:2306.06085 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5334"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511861.3511863"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Boris A Galitsky. 2023. Truth-O-Meter: Collaborating with LLM in Fighting its Hallucinations. (2023).","DOI":"10.20944\/preprints202307.1723.v1"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177705148"},{"key":"e_1_3_2_1_29_1","volume-title":"Critic: Large language models can self-correct with tool-interactive critiquing. arXiv preprint arXiv:2305.11738","author":"Gou Zhibin","year":"2023","unstructured":"Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Nan Duan, and Weizhu Chen. 2023. Critic: Large language models can self-correct with tool-interactive critiquing. arXiv preprint arXiv:2305.11738 (2023)."},{"key":"e_1_3_2_1_30_1","volume-title":"Natural language question answering: the view from here. natural language engineering 7, 4","author":"Hirschman Lynette","year":"2001","unstructured":"Lynette Hirschman and Robert Gaizauskas. 2001. Natural language question answering: the view from here. natural language engineering 7, 4 (2001), 275--300."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3238147.3238208"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. 3680--3696","author":"Jang Myeongjun","year":"2022","unstructured":"Myeongjun Jang, Deuk Sin Kwon, and Thomas Lukasiewicz. 2022. BECEL: Benchmark for Consistency Evaluation of Language Models. In Proceedings of the 29th International Conference on Computational Linguistics. 3680--3696."},{"key":"e_1_3_2_1_33_1","volume-title":"Consistency analysis of chatgpt. arXiv preprint arXiv:2303.06273","author":"Jang Myeongjun","year":"2023","unstructured":"Myeongjun Jang and Thomas Lukasiewicz. 2023. Consistency analysis of chatgpt. arXiv preprint arXiv:2303.06273 (2023)."},{"key":"e_1_3_2_1_34_1","volume-title":"Adversarial examples for evaluating reading comprehension systems. arXiv preprint arXiv:1707.07328","author":"Jia Robin","year":"2017","unstructured":"Robin Jia and Percy Liang. 2017. Adversarial examples for evaluating reading comprehension systems. arXiv preprint arXiv:1707.07328 (2017)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00407"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3559548"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER56733.2023.00071"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/acp.2879"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3409711"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"e_1_3_2_1_41_1","first-page":"34586","article-title":"Factuality enhanced language models for open-ended text generation","volume":"35","author":"Lee Nayeon","year":"2022","unstructured":"Nayeon Lee, Wei Ping, Peng Xu, Mostofa Patwary, Pascale N Fung, Mohammad Shoeybi, and Bryan Catanzaro. 2022. Factuality enhanced language models for open-ended text generation. Advances in Neural Information Processing Systems 35 (2022), 34586--34599.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2022.111255"},{"key":"e_1_3_2_1_43_1","volume-title":"Teaching models to express their uncertainty in words. arXiv preprint arXiv:2205.14334","author":"Lin Stephanie","year":"2022","unstructured":"Stephanie Lin, Jacob Hilton, and Owain Evans. 2022. Teaching models to express their uncertainty in words. arXiv preprint arXiv:2205.14334 (2022)."},{"key":"e_1_3_2_1_44_1","volume-title":"Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models. arXiv preprint arXiv:2305.19187","author":"Lin Zhen","year":"2023","unstructured":"Zhen Lin, Shubhendu Trivedi, and Jimeng Sun. 2023. Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models. arXiv preprint arXiv:2305.19187 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Yuyao Wang, and Lingming Zhang.","author":"Liu Jiawei","year":"2023","unstructured":"Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. 2023. Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation. arXiv preprint arXiv:2305.01210 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3120203"},{"key":"e_1_3_2_1_47_1","volume-title":"Entity-based knowledge conflicts in question answering. arXiv preprint arXiv:2109.05052","author":"Longpre Shayne","year":"2021","unstructured":"Shayne Longpre, Kartik Perisetla, Anthony Chen, Nikhil Ramesh, Chris DuBois, and Sameer Singh. 2021. Entity-based knowledge conflicts in question answering. arXiv preprint arXiv:2109.05052 (2021)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3501709.3544280"},{"key":"e_1_3_2_1_49_1","volume-title":"Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896","author":"Manakul Potsawee","year":"2023","unstructured":"Potsawee Manakul, Adian Liusie, and Mark JF Gales. 2023. Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models. arXiv preprint arXiv:2303.08896 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00494"},{"key":"e_1_3_2_1_51_1","unstructured":"OpenAI. [n. d.]. Online-ChatGPT - Optimizing Language Models for Dialogue. https:\/\/online-chatgpt.com\/. [Accessed 31-07-2023]."},{"key":"e_1_3_2_1_52_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_53_1","volume-title":"Stack Overflow Search. Stack Overflow, https:\/\/stackoverflow.com\/search. Last updated on","author":"Overflow Stack","year":"2023","unstructured":"Stack Overflow. 2023. Stack Overflow Search. Stack Overflow, https:\/\/stackoverflow.com\/search. Last updated on 01 August 2023."},{"key":"e_1_3_2_1_54_1","volume-title":"Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334","author":"Patil Shishir G","year":"2023","unstructured":"Shishir G Patil, Tianjun Zhang, Xin Wang, and Joseph E Gonzalez. 2023. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179420"},{"key":"e_1_3_2_1_56_1","unstructured":"Baolin Peng Michel Galley Pengcheng He Hao Cheng Yujia Xie Yu Hu Qiuyuan Huang Lars Liden Zhou Yu Weizhu Chen et al. 2023. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:2302.12813 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nlp4prog-1.5"},{"key":"e_1_3_2_1_58_1","volume-title":"Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugs. arXiv preprint arXiv:2111.03922","author":"Prenner Julian Aron","year":"2021","unstructured":"Julian Aron Prenner and Romain Robbes. 2021. Automatic Program Repair with OpenAI's Codex: Evaluating QuixBugs. arXiv preprint arXiv:2111.03922 (2021)."},{"key":"e_1_3_2_1_59_1","volume-title":"Beyond accuracy: Behavioral testing of NLP models with CheckList. arXiv preprint arXiv:2005.04118","author":"Ribeiro Marco Tulio","year":"2020","unstructured":"Marco Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin, and Sameer Singh. 2020. Beyond accuracy: Behavioral testing of NLP models with CheckList. arXiv preprint arXiv:2005.04118 (2020)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556953"},{"key":"e_1_3_2_1_61_1","volume-title":"ChatGPT Incorrectness Detection in Software Reviews","author":"Tanzil Minaoar Hossain","unstructured":"Minaoar Hossain Tanzil. 2023. ChatGPT Incorrectness Detection in Software Reviews. University of Calgary, https:\/\/github.com\/minaoar\/ChatGPT-Incorrectness-Detection-in-Software-Reviews."},{"key":"e_1_3_2_1_62_1","volume-title":"Xunzhu Tang, Shing-Chi Cheung, Jacques Klein, and Tegawend\u00e9 F Bissyand\u00e9.","author":"Tian Haoye","year":"2023","unstructured":"Haoye Tian, Weiqi Lu, Tsz On Li, Xunzhu Tang, Shing-Chi Cheung, Jacques Klein, and Tegawend\u00e9 F Bissyand\u00e9. 2023. Is ChatGPT the Ultimate Programming Assistant-How far is it? arXiv preprint arXiv:2304.11938 (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2019.2903039"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115629"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2017.8115715"},{"key":"e_1_3_2_1_66_1","volume-title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation. arXiv preprint arXiv:2307.03987","author":"Varshney Neeraj","year":"2023","unstructured":"Neeraj Varshney, Wenlin Yao, Hongming Zhang, Jianshu Chen, and Dong Yu. 2023. A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation. arXiv preprint arXiv:2307.03987 (2023)."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1177\/0963721410391245"},{"key":"e_1_3_2_1_68_1","volume-title":"Samantha Mann, Ronald P Fisher, Jackie Hillman, and Kathryn Sperry.","author":"Vrij Aldert","year":"2009","unstructured":"Aldert Vrij, Sharon Leal, P\u00e4r Anders Granhag, Samantha Mann, Ronald P Fisher, Jackie Hillman, and Kathryn Sperry. 2009. Outsmarting the liars: The benefit of asking unanticipated questions. Law and human behavior 33 (2009), 159--166."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-8639"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368089.3417931"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3059885"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.685"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57735-7_18"},{"key":"e_1_3_2_1_74_1","volume-title":"Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT. arXiv preprint arXiv:2304.00385","author":"Xia Chunqiu Steven","year":"2023","unstructured":"Chunqiu Steven Xia and Lingming Zhang. 2023. Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT. arXiv preprint arXiv:2304.00385 (2023)."},{"key":"e_1_3_2_1_75_1","volume-title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs. arXiv preprint arXiv:2306.13063","author":"Xiong Miao","year":"2023","unstructured":"Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, and Bryan Hooi. 2023. Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs. arXiv preprint arXiv:2306.13063 (2023)."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545647"},{"key":"e_1_3_2_1_77_1","volume-title":"How language model hallucinations can snowball. arXiv preprint arXiv:2305.13534","author":"Zhang Muru","year":"2023","unstructured":"Muru Zhang, Ofir Press, William Merrill, Alisa Liu, and Noah A Smith. 2023. How language model hallucinations can snowball. arXiv preprint arXiv:2305.13534 (2023)."},{"key":"e_1_3_2_1_78_1","volume-title":"Machine reading comprehension: The role of contextualized language models and beyond. arXiv preprint arXiv:2005.06249","author":"Zhang Zhuosheng","year":"2020","unstructured":"Zhuosheng Zhang, Hai Zhao, and Rui Wang. 2020. Machine reading comprehension: The role of contextualized language models and beyond. arXiv preprint arXiv:2005.06249 (2020)."}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639194","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3639194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:13Z","timestamp":1750286953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639194"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":78,"alternative-id":["10.1145\/3597503.3639194","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3639194","relation":{},"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}