{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:47:24Z","timestamp":1777873644916,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":15,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737854","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T20:54:17Z","timestamp":1754254457000},"page":"6286-6287","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["KDD Workshop on Evaluation and Trustworthiness of Agentic and Generative AI"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1135-5240","authenticated-orcid":false,"given":"Yuan","family":"Ling","sequence":"first","affiliation":[{"name":"Amazon, Bellevue, 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, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4406-2193","authenticated-orcid":false,"given":"Zheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Amazon, Bellevue, 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, Bellevue, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5665-7752","authenticated-orcid":false,"given":"Sadid","family":"Hasan","sequence":"additional","affiliation":[{"name":"Microsoft, Boston, MA, 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":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Anthropic. 2024. Introducing Claude 3. Technical Report. Anthropic. https:\/\/www.anthropic.com\/news\/claude-3-family Accessed: 2024-01-09."},{"key":"e_1_3_2_1_2_1","unstructured":"DeepSeek-AI and etc. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. arXiv:2501.12948 [cs.CL] https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"e_1_3_2_1_3_1","volume-title":"Bidipta Sarkar, Rohan Taori, Yusuke Noda, Demetri Terzopoulos, Yejin Choi, et al.","author":"Durante Zane","year":"2024","unstructured":"Zane Durante, Qiuyuan Huang, Naoki Wake, Ran Gong, Jae Sung Park, Bidipta Sarkar, Rohan Taori, Yusuke Noda, Demetri Terzopoulos, Yejin Choi, et al. 2024. Agent ai: Surveying the horizons of multimodal interaction. arXiv preprint arXiv:2401.03568 (2024)."},{"key":"e_1_3_2_1_4_1","unstructured":"Jiawei Gu Xuhui Jiang Zhichao Shi Hexiang Tan Xuehao Zhai Chengjin Xu Wei Li Yinghan Shen Shengjie Ma Honghao Liu et al. 2024. A Survey on LLM-as-a-Judge. arXiv preprint arXiv:2411.15594 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_6_1","unstructured":"Dawei Li Bohan Jiang Liangjie Huang Alimohammad Beigi Chengshuai Zhao Zhen Tan Amrita Bhattacharjee Yuxuan Jiang Canyu Chen Tianhao Wu Kai Shu Lu Cheng and Huan Liu. 2025. From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge. arXiv:2411.16594 [cs.AI] https:\/\/arxiv.org\/ abs\/2411.16594"},{"key":"e_1_3_2_1_7_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_1_8_1","volume-title":"GLIDE: Towards Photorealistic 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 Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arXiv:2112.10741 [cs.CV]"},{"key":"e_1_3_2_1_9_1","unstructured":"OpenAI 2023. ChatGPT. https:\/\/chat.openai.com\/ Accessed: 2023-04--20."},{"key":"e_1_3_2_1_10_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."},{"key":"e_1_3_2_1_11_1","unstructured":"OpenAI and etc. 2023. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL]"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"William Peebles and Saining Xie. 2023. Scalable Diffusion Models with Transformers. arXiv:2212.09748 [cs.CV]","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_13_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]"},{"key":"e_1_3_2_1_14_1","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]","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_15_1","first-page":"46595","article-title":"2023. Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems 36 (2023), 46595-46623.","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:08:22Z","timestamp":1777572502000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":15,"alternative-id":["10.1145\/3711896.3737854","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737854","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}