{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:23:05Z","timestamp":1787689385409,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3785704","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"2830-2841","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0936-0681","authenticated-orcid":false,"given":"Chengxu","family":"Yang","sequence":"first","affiliation":[{"name":"Wuhan University of Technology, Wuhan, Hubei, China and BreathingCORE, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7924-8620","authenticated-orcid":false,"given":"Jingling","family":"Yuan","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7978-8475","authenticated-orcid":false,"given":"Siqi","family":"Cai","sequence":"additional","affiliation":[{"name":"Wuhan University of Technology, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0051-0046","authenticated-orcid":false,"given":"Jiawei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9051-3242","authenticated-orcid":false,"given":"Chuang","family":"Hu","sequence":"additional","affiliation":[{"name":"Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1177\/0149206318805832"},{"key":"e_1_3_2_2_2_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41594-023-01112-6"},{"key":"e_1_3_2_2_4_1","first-page":"547","volume-title":"Nature","volume":"600","author":"Anishchenko Ivan","year":"2021","unstructured":"Ivan Anishchenko, Samuel J Pellock, Tamuka M Chidyausiku, Theresa A Ramelot, Sergey Ovchinnikov, Jingzhou Hao, Khushboo Bafna, Christoffer Norn, Alex Kang, Asim K Bera, et al., 2021. De novo protein design by deep network hallucination. Nature, Vol. 600, 7889 (2021), 547-552."},{"key":"e_1_3_2_2_5_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"HalluLens: LLM Hallucination Benchmark. arXiv preprint arXiv:2504.17550","author":"Bang Yejin","year":"2025","unstructured":"Yejin Bang, Ziwei Ji, Alan Schelten, Anthony Hartshorn, Tara Fowler, Cheng Zhang, Nicola Cancedda, and Pascale Fung. 2025. HalluLens: LLM Hallucination Benchmark. arXiv preprint arXiv:2504.17550 (2025)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","unstructured":"Forrest Bao Miaoran Li Rogger Luo and Ofer Mendelevitch. 2024. HHEM-2.1-Open. doi:10.57967\/hf\/3240","DOI":"10.57967\/hf\/3240"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0048073"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642731"},{"key":"e_1_3_2_2_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_2_11_1","unstructured":"Qinyuan Cheng Tianxiang Sun Wenwei Zhang Siyin Wang Xiangyang Liu Mozhi Zhang Junliang He Mianqiu Huang Zhangyue Yin Kai Chen et al. 2023. Evaluating hallucinations in chinese large language models. arXiv preprint arXiv:2310.03368 (2023)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.54254\/2753-7064\/35\/20240006"},{"key":"e_1_3_2_2_13_1","volume-title":"Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821","author":"Gao Tianyu","year":"2021","unstructured":"Tianyu Gao, Xingcheng Yao, and Danqi Chen. 2021. Simcse: Simple contrastive learning of sentence embeddings. arXiv preprint arXiv:2104.08821 (2021)."},{"key":"e_1_3_2_2_14_1","volume-title":"American psychologist","author":"Guilford Joy Paul","year":"1950","unstructured":"Joy Paul Guilford. 1950. Creativity. American psychologist, Vol. 5, 9 (1950)."},{"key":"e_1_3_2_2_15_1","unstructured":"Joy Paul Guilford. 1967. The nature of human intelligence. (1967)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29771"},{"key":"e_1_3_2_2_17_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_2_2_18_1","volume-title":"Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680","author":"Guo Taicheng","year":"2024","unstructured":"Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. Large language model based multi-agents: A survey of progress and challenges. arXiv preprint arXiv:2402.01680 (2024)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3660685"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3481"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_3_2_2_22_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_2_23_1","volume-title":"Creativity in AI: Progresses and Challenges. arXiv preprint arXiv:2410.17218","author":"Ismayilzada Mete","year":"2024","unstructured":"Mete Ismayilzada, Debjit Paul, Antoine Bosselut, and Lonneke van der Plas. 2024. Creativity in AI: Progresses and Challenges. arXiv preprint arXiv:2410.17218 (2024)."},{"key":"e_1_3_2_2_24_1","volume-title":"A survey on large language model hallucination via a creativity perspective. arXiv preprint arXiv:2402.06647","author":"Jiang Xuhui","year":"2024","unstructured":"Xuhui Jiang, Yuxing Tian, Fengrui Hua, Chengjin Xu, Yuanzhuo Wang, and Jian Guo. 2024. A survey on large language model hallucination via a creativity perspective. arXiv preprint arXiv:2402.06647 (2024)."},{"key":"e_1_3_2_2_25_1","volume-title":"Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa.","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems, Vol. 35 (2022), 22199-22213."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/math11102320"},{"key":"e_1_3_2_2_27_1","volume-title":"Llms-as-judges: a comprehensive survey on llm-based evaluation methods. arXiv preprint arXiv:2412.05579","author":"Li Haitao","year":"2024","unstructured":"Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, and Yiqun Liu. 2024. Llms-as-judges: a comprehensive survey on llm-based evaluation methods. arXiv preprint arXiv:2412.05579 (2024)."},{"key":"e_1_3_2_2_28_1","volume-title":"Jian-Yun Nie, and Ji-Rong Wen.","author":"Li Junyi","year":"2023","unstructured":"Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, and Ji-Rong Wen. 2023. Halueval: A large-scale hallucination evaluation benchmark for large language models. arXiv preprint arXiv:2305.11747 (2023)."},{"key":"e_1_3_2_2_29_1","volume-title":"Uhgeval: Benchmarking the hallucination of chinese large language models via unconstrained generation. arXiv preprint arXiv:2311.15296","author":"Liang Xun","year":"2023","unstructured":"Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Peng Cheng, Zhonghao Wang, et al., 2023. Uhgeval: Benchmarking the hallucination of chinese large language models via unconstrained generation. arXiv preprint arXiv:2311.15296 (2023)."},{"key":"e_1_3_2_2_30_1","volume-title":"Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958","author":"Lin Stephanie","year":"2021","unstructured":"Stephanie Lin, Jacob Hilton, and Owain Evans. 2021. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958 (2021)."},{"key":"e_1_3_2_2_31_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_2_32_1","volume-title":"Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View. In The Thirteenth International Conference on Learning Representations.","author":"Liu Xuan","unstructured":"Xuan Liu, Jie ZHANG, HaoYang Shang, Song Guo, Yang Chengxu, and Quanyan Zhu. [n.d.]. Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_2_33_1","volume-title":"Llm discussion: Enhancing the creativity of large language models via discussion framework and role-play. arXiv preprint arXiv:2405.06373","author":"Lu Li-Chun","year":"2024","unstructured":"Li-Chun Lu, Shou-Jen Chen, Tsung-Min Pai, Chan-Hung Yu, Hung-yi Lee, and Shao-Hua Sun. 2024. Llm discussion: Enhancing the creativity of large language models via discussion framework and role-play. arXiv preprint arXiv:2405.06373 (2024)."},{"key":"e_1_3_2_2_34_1","volume-title":"Halludial: A large-scale benchmark for automatic dialogue-level hallucination evaluation. arXiv preprint arXiv:2406.07070","author":"Luo Wen","year":"2024","unstructured":"Wen Luo, Tianshu Shen, Wei Li, Guangyue Peng, Richeng Xuan, Houfeng Wang, and Xi Yang. 2024. Halludial: A large-scale benchmark for automatic dialogue-level hallucination evaluation. arXiv preprint arXiv:2406.07070 (2024)."},{"key":"e_1_3_2_2_35_1","volume-title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models. In The 2023 Conference on Empirical Methods in Natural Language Processing.","author":"Manakul Potsawee","unstructured":"Potsawee Manakul, Adian Liusie, and Mark Gales. [n.d.]. SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models. In The 2023 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.741"},{"key":"e_1_3_2_2_37_1","volume-title":"Measuring and narrowing the compositionality gap in language models. arXiv preprint arXiv:2210.03350","author":"Press Ofir","year":"2022","unstructured":"Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A Smith, and Mike Lewis. 2022. Measuring and narrowing the compositionality gap in language models. arXiv preprint arXiv:2210.03350 (2022)."},{"key":"e_1_3_2_2_38_1","volume-title":"A survey of hallucination in large foundation models. arXiv preprint arXiv:2309.05922","author":"Rawte Vipula","year":"2023","unstructured":"Vipula Rawte, Amit Sheth, and Amitava Das. 2023. A survey of hallucination in large foundation models. arXiv preprint arXiv:2309.05922 (2023)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.432"},{"key":"e_1_3_2_2_40_1","volume-title":"LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context. arXiv preprint arXiv:2412.17596","author":"Ruan Kai","year":"2024","unstructured":"Kai Ruan, Xuan Wang, Jixiang Hong, Peng Wang, Yang Liu, and Hao Sun. 2024. LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context. arXiv preprint arXiv:2412.17596 (2024)."},{"key":"e_1_3_2_2_41_1","volume-title":"Creativity and culture. The journal of psychology","author":"Stein Morris I","year":"1953","unstructured":"Morris I Stein. 1953. Creativity and culture. The journal of psychology, Vol. 36, 2 (1953), 311-322."},{"key":"e_1_3_2_2_42_1","volume-title":"Torrance tests of creative thinking. Educational and psychological measurement","author":"Torrance E Paul","year":"1966","unstructured":"E Paul Torrance. 1966. Torrance tests of creative thinking. Educational and psychological measurement (1966)."},{"key":"e_1_3_2_2_43_1","volume-title":"Zain Muhammad Mujahid, Arnav Arora, Aleksandr Rubashevskii, Jiahui Geng, Osama Mohammed Afzal, Liangming Pan, Nadav Borenstein, Aditya Pillai, et al.","author":"Wang Yuxia","year":"2024","unstructured":"Yuxia Wang, Revanth Gangi Reddy, Zain Muhammad Mujahid, Arnav Arora, Aleksandr Rubashevskii, Jiahui Geng, Osama Mohammed Afzal, Liangming Pan, Nadav Borenstein, Aditya Pillai, et al., 2024. Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers. In EMNLP (Findings)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4222-0"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058927"},{"key":"e_1_3_2_2_46_1","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et al. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_2_2_47_1","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_2_48_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","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 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3785704","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:02:41Z","timestamp":1787688161000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3785704"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":48,"alternative-id":["10.1145\/3770854.3785704","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3785704","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}