{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:02:16Z","timestamp":1750309336158,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":23,"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"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671481","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"6729-6730","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["KDD workshop on Evaluation and Trustworthiness of Generative AI Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1135-5240","authenticated-orcid":false,"given":"Yuan","family":"Ling","sequence":"first","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0240-681X","authenticated-orcid":false,"given":"Shujing","family":"Dong","sequence":"additional","affiliation":[{"name":"Amazon, Irvine, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7595-6945","authenticated-orcid":false,"given":"Yarong","family":"Feng","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8194-8278","authenticated-orcid":false,"given":"Zongyi (Joe)","family":"Liu","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2753-1437","authenticated-orcid":false,"given":"George","family":"Karypis","sequence":"additional","affiliation":[{"name":"Univ. of Minnesota \/ Amazon, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2839-3662","authenticated-orcid":false,"given":"Chandan K.","family":"Reddy","sequence":"additional","affiliation":[{"name":"Virginia Tech \/ Amazon, Arlington, VA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"unstructured":"Ebtesam Almazrouei Hamza Alobeidli Abdulaziz Alshamsi Alessandro Cappelli Ruxandra Cojocaru Merouane Debbah Etienne Goffinet Daniel Heslow Julien Launay Quentin Malartic Badreddine Noune Baptiste Pannier and Guilherme Penedo. 2023. Falcon-40B: an open large language model with state-of-the-art performance. (2023).","key":"e_1_3_2_1_1_1"},{"unstructured":"Anthropic. 2023. Model Card and Evaluations for Claude Models. https:\/\/www-files.anthropic.com\/production\/images\/Model-Card-Claude-2.pdf. Accessed: 2023--12-05.","key":"e_1_3_2_1_2_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_3_1"},{"key":"e_1_3_2_1_4_1","volume-title":"et al","author":"Chang Yupeng","year":"2023","unstructured":"Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, et al . 2023. A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology (2023)."},{"doi-asserted-by":"publisher","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Eric Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling Instruction-Finetuned Language Models. https:\/\/doi.org\/10.48550\/ARXIV.2210.11416","key":"e_1_3_2_1_5_1","DOI":"10.48550\/ARXIV.2210.11416"},{"key":"e_1_3_2_1_6_1","volume-title":"Opencompass: A universal evaluation platform for foundation models. GitHub repository","author":"Contributors OpenCompass","year":"2023","unstructured":"OpenCompass Contributors. 2023. Opencompass: A universal evaluation platform for foundation models. GitHub repository (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues. arXiv preprint arXiv:2310.13650","author":"Duan Haodong","year":"2023","unstructured":"Haodong Duan, Jueqi Wei, Chonghua Wang, Hongwei Liu, Yixiao Fang, Songyang Zhang, Dahua Lin, and Kai Chen. 2023. BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues. arXiv preprint arXiv:2310.13650 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"LLM-based NLG Evaluation: Current Status and Challenges. arXiv preprint arXiv:2402.01383","author":"Gao Mingqi","year":"2024","unstructured":"Mingqi Gao, Xinyu Hu, Jie Ruan, Xiao Pu, and Xiaojun Wan. 2024. LLM-based NLG Evaluation: Current Status and Challenges. arXiv preprint arXiv:2402.01383 (2024)."},{"unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. arXiv:2006.11239 [cs.LG]","key":"e_1_3_2_1_9_1"},{"unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-Free Diffusion Guidance. arXiv:2207.12598 [cs.LG]","key":"e_1_3_2_1_10_1"},{"unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar et al. 2022. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110 (2022).","key":"e_1_3_2_1_11_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1145\/3580305.3599208"},{"key":"e_1_3_2_1_13_1","volume-title":"Yegor Klochkov, Muhammad Faaiz Taufiq, and Hang Li.","author":"Liu Yang","year":"2023","unstructured":"Yang Liu, Yuanshun Yao, Jean-Francois Ton, Xiaoying Zhang, Ruocheng Guo Hao Cheng, Yegor Klochkov, Muhammad Faaiz Taufiq, and Hang Li. 2023. Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment. arXiv preprint arXiv:2308.05374 (2023)."},{"key":"e_1_3_2_1_14_1","volume-title":"GLIDE: Towards Photo- realistic Image Generation and Editing with Text-Guided Diffusion Models. arXiv:2112.10741 [cs.CV]","author":"Nichol Alex","year":"2022","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2022. GLIDE: Towards Photo- realistic Image Generation and Editing with Text-Guided Diffusion Models. arXiv:2112.10741 [cs.CV]"},{"unstructured":"OpenAI 2023. ChatGPT. https:\/\/chat.openai.com\/ Accessed: 2023-04--20.","key":"e_1_3_2_1_15_1"},{"key":"e_1_3_2_1_16_1","volume-title":"Sora: Creating video from text. https:\/\/openai.com\/sora. Accessed: 2024-02--24.","author":"AI.","year":"2024","unstructured":"OpenAI. 2024. Sora: Creating video from text. https:\/\/openai.com\/sora. Accessed: 2024-02--24."},{"doi-asserted-by":"crossref","unstructured":"William Peebles and Saining Xie. 2023. Scalable Diffusion Models with Transformers. arXiv:2212.09748 [cs.CV]","key":"e_1_3_2_1_18_1","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_19_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV]","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. arXiv:2307.01952 [cs.CV]"},{"doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. arXiv:2112.10752 [cs.CV]","key":"e_1_3_2_1_20_1","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_21_1","volume-title":"Trustllm: Trust-worthiness in large language models. arXiv preprint arXiv:2401.05561","author":"Sun Lichao","year":"2024","unstructured":"Lichao Sun, Yue Huang, Haoran Wang, Siyuan Wu, Qihui Zhang, Chujie Gao, Yixin Huang, Wenhan Lyu, Yixuan Zhang, Xiner Li, et al. 2024. Trustllm: Trust-worthiness in large language models. arXiv preprint arXiv:2401.05561 (2024)."},{"unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023).","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","volume-title":"Mint: Evaluating llms in multi-turn interaction with tools and language feedback. arXiv preprint arXiv:2309.10691","author":"Wang Xingyao","year":"2023","unstructured":"Xingyao Wang, Zihan Wang, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng, and Heng Ji. 2023. Mint: Evaluating llms in multi-turn interaction with tools and language feedback. arXiv preprint arXiv:2309.10691 (2023)."},{"key":"e_1_3_2_1_24_1","volume-title":"Prompt-bench: A unified library for evaluation of large language models. arXiv preprint arXiv:2312.07910","author":"Zhu Kaijie","year":"2023","unstructured":"Kaijie Zhu, Qinlin Zhao, Hao Chen, Jindong Wang, and Xing Xie. 2023. Prompt-bench: A unified library for evaluation of large language models. arXiv preprint arXiv:2312.07910 (2023)."}],"event":{"sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"acronym":"KDD '24","name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain"},"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\/3637528.3671481","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:18Z","timestamp":1750291458000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671481"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":23,"alternative-id":["10.1145\/3637528.3671481","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671481","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"}}]}}