{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:10:04Z","timestamp":1755889804740,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","funder":[{"name":"Strategic Priority Research Program of the CAS","award":["No. XDB0680302"],"award-info":[{"award-number":["No. XDB0680302"]}]},{"name":"The National Natural Science Foundation of China","award":["No.62202448"],"award-info":[{"award-number":["No.62202448"]}]},{"name":"The National Key R&D Program of China","award":["No.2022YFB3103700, No. 2022YFB3103704"],"award-info":[{"award-number":["No.2022YFB3103700, No. 2022YFB3103704"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730195","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:18:36Z","timestamp":1752455916000},"page":"2807-2811","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Fact-Level Calibration and Correction for Long-Form Generations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8856-668X","authenticated-orcid":false,"given":"Yige","family":"Yuan","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0147-2590","authenticated-orcid":false,"given":"Bingbing","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9104-3871","authenticated-orcid":false,"given":"Hexiang","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6146-148X","authenticated-orcid":false,"given":"Fei","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9180-1433","authenticated-orcid":false,"given":"Teng","family":"Xiao","sequence":"additional","affiliation":[{"name":"Independent Researcher, State College, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4464-2446","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2425-1499","authenticated-orcid":false,"given":"Huawei","family":"Shen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-8195","authenticated-orcid":false,"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"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).","key":"e_1_3_2_1_1_1","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"e_1_3_2_1_2_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.48550\/ARXIV.2311.17311"},{"key":"e_1_3_2_1_4_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.18653\/v1\/2024.naacl-long.366"},{"key":"e_1_3_2_1_6_1","volume-title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Golovneva Olga","year":"2023","unstructured":"Olga Golovneva, Moya Chen, Spencer Poff, Martin Corredor, Luke Zettlemoyer, Maryam Fazel-Zarandi, and Asli Celikyilmaz. 2023. ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=xYlJRpzZtsY"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger. 2017. On Calibration of Modern Neural Networks. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017 (Proceedings of Machine Learning Research, Vol. 70), Doina Precup and Yee Whye Teh (Eds.). PMLR, 1321-1330. http:\/\/proceedings.mlr.press\/v70\/guo17a.html"},{"volume-title":"Google and the Culture of Search","author":"Hillis Ken","unstructured":"Ken Hillis, Michael Petit, and Kylie Jarrett. 2012. Google and the Culture of Search. Routledge.","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","volume-title":"Calibrating Long-form Generations from Large Language Models. arXiv preprint arXiv:2402.06544","author":"Huang Yukun","year":"2024","unstructured":"Yukun Huang, Yixin Liu, Raghuveer Thirukovalluru, Arman Cohan, and Bhuwan Dhingra. 2024. Calibrating Long-form Generations from Large Language Models. arXiv preprint arXiv:2402.06544 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Roger Baker Grosse, and Jimmy Ba","author":"Jiang Mingjian","year":"2023","unstructured":"Mingjian Jiang, Yangjun Ruan, Sicong Huang, Saifei Liao, Silviu Pitis, Roger Baker Grosse, and Jimmy Ba. 2023. Calibrating Language Models via Augmented Prompt Ensembles. (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.48550\/arXiv.2207.05221"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.48550\/ARXIV.2403.09972"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_14_1","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"e_1_3_2_1_15_1","volume-title":"Lightweight Language Model Calibration for Open-ended Question Answering with Varied Answer Lengths. In The Twelfth International Conference on Learning Representations.","author":"Liu Xin","year":"2023","unstructured":"Xin Liu, Muhammad Khalifa, and Lu Wang. 2023. Lightweight Language Model Calibration for Open-ended Question Answering with Varied Answer Lengths. In The Twelfth International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.48550\/arXiv.2305.14251"},{"key":"e_1_3_2_1_18_1","volume-title":"Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation. arXiv preprint arXiv:2305.15852","author":"M\u00fcndler Niels","year":"2023","unstructured":"Niels M\u00fcndler, Jingxuan He, Slobodan Jenko, and Martin Vechev. 2023. Self-contradictory hallucinations of large language models: Evaluation, detection and mitigation. arXiv preprint arXiv:2305.15852 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_19_1","DOI":"10.18653\/v1\/d15-1182"},{"unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR Vol. abs\/2303.08774 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.08774 arXiv:2303.08774","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","volume-title":"Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. CoRR","author":"Powers David M. W.","year":"2020","unstructured":"David M. W. Powers. 2020. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. CoRR, Vol. abs\/2010.16061 (2020). arXiv:2010.16061 https:\/\/arxiv.org\/abs\/2010.16061"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.566"},{"key":"e_1_3_2_1_23_1","volume-title":"Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. arXiv preprint arXiv:2305.14975","author":"Tian Katherine","year":"2023","unstructured":"Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, and Christopher D Manning. 2023. Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. arXiv preprint arXiv:2305.14975 (2023)."},{"doi-asserted-by":"publisher","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton-Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas and et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. CoRR Vol. abs\/2307.09288 (2023). https:\/\/doi.org\/10.48550\/arXiv.2307.09288 arXiv:2307.09288","key":"e_1_3_2_1_24_1","DOI":"10.48550\/arXiv.2307.09288"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.48550\/ARXIV.2402.15631"},{"unstructured":"Jerry Wei Chengrun Yang Xinying Song Yifeng Lu Nathan Hu Dustin Tran Daiyi Peng Ruibo Liu Da Huang Cosmo Du et al. 2024. Long-form factuality in large language models. arXiv preprint arXiv:2403.18802 (2024).","key":"e_1_3_2_1_26_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.18653\/v1\/2024.emnlp-main.744"},{"key":"e_1_3_2_1_28_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=jfwe9qNqRi","author":"Xiao Teng","year":"2025","unstructured":"Teng Xiao, Yige Yuan, Zhengyu Chen, Mingxiao Li, Shangsong Liang, Zhaochun Ren, and Vasant G Honavar. 2025 a. SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=jfwe9qNqRi"},{"key":"e_1_3_2_1_29_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2QdsjiNXgj","author":"Xiao Teng","year":"2025","unstructured":"Teng Xiao, Yige Yuan, Mingxiao Li, Zhengyu Chen, and Vasant G Honavar. 2025 b. On a Connection Between Imitation Learning and RLHF. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=2QdsjiNXgj"},{"key":"e_1_3_2_1_30_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Xiao Teng","year":"2024","unstructured":"Teng Xiao, Yige Yuan, Huaisheng Zhu, Mingxiao Li, and Vasant G Honavar. 2024b. Cal-dpo: Calibrated direct preference optimization for language model alignment. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_31_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)."},{"volume-title":"Inference-time Alignment in Continuous Space. In ICLR 2025 Workshop on Bidirectional Human-AI Alignment.","author":"Yuan Yige","unstructured":"Yige Yuan, Teng Xiao, Li Yunfan, Xu Bingbing, Shuchang Tao, Yunqi Qiu, Huawei Shen, and Xueqi Cheng. [n.d.]. Inference-time Alignment in Continuous Space. In ICLR 2025 Workshop on Bidirectional Human-AI Alignment.","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 11117-11128","author":"Zhang Jize","year":"2020","unstructured":"Jize Zhang, Bhavya Kailkhura, and T Yong-Jin Han. 2020. Mix-n-match: Ensemble and compositional methods for uncertainty calibration in deep learning. In International conference on machine learning. PMLR, 11117-11128."},{"unstructured":"Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Tingchen Fu Xinting Huang Enbo Zhao Yu Zhang Yulong Chen et al. 2023. Siren's song in the ai ocean: A survey on hallucination in large language models. arXiv preprint arXiv:2309.01219 (2023).","key":"e_1_3_2_1_34_1"}],"event":{"sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"acronym":"SIGIR '25","name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy"},"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\/3726302.3730195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:34:25Z","timestamp":1755887665000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":34,"alternative-id":["10.1145\/3726302.3730195","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730195","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"}}]}}