{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:13:31Z","timestamp":1783523611676,"version":"3.55.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032308481","type":"print"},{"value":"9783032308498","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-30849-8_24","type":"book-chapter","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:15:40Z","timestamp":1783520140000},"page":"405-419","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Debate-Driven Evaluation of\u00a0LLMs: Challenges and\u00a0Opportunities for\u00a0Transparency and\u00a0Human\u2013AI Collaboration"],"prefix":"10.1007","author":[{"given":"Siqi","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Boyapati, M., et al.: LevelEval: adaptive pipeline for evaluating LLM as a judge-analysis on open LLMs as judges. In: 2024 International Conference on AI x Data and Knowledge Engineering (AIxDKE), pp. 74\u201377. IEEE (2024)","DOI":"10.1109\/AIxDKE63520.2024.00020"},{"key":"24_CR2","unstructured":"Chan, C.M., et al.: ChatEval: towards better LLM-based evaluators through multi-agent debate. arXiv preprint: arXiv:2308.07201 (2023)"},{"issue":"3","key":"24_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","volume":"15","author":"Y Chang","year":"2024","unstructured":"Chang, Y., et al.: A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15(3), 1\u201345 (2024)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"24_CR4","unstructured":"Chern, S., Chern, E., Neubig, G., Liu, P.: Can large language models be trusted for evaluation? Scalable meta-evaluation of LLMs as evaluators via agent debate. arXiv preprint: arXiv:2401.16788 (2024)"},{"key":"24_CR5","unstructured":"Chiang, W.L., et al.: Chatbot arena: an open platform for evaluating LLMs by human preference. In: Forty-first International Conference on Machine Learning (2024). https:\/\/openreview.net\/forum?id=3MW8GKNyzI"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Estornell, A., Liu, Y.: Multi-llm debate: Framework, principals, and interventions. In: Advances in Neural Information Processing Systems, vol. 37, pp. 28938\u201328964 (2024)","DOI":"10.52202\/079017-0911"},{"key":"24_CR7","unstructured":"Gu, J., et\u00a0al.: A survey on LLM-as-a-judge. arXiv preprint: arXiv:2411.15594 (2024)"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Kenton, Z., et al.: On scalable oversight with weak LLMs judging strong LLMs. In: Advances in Neural Information Processing Systems, vol. 37, pp. 75229\u201375276 (2024)","DOI":"10.52202\/079017-2395"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Li, D., et\u00a0al.: From generation to judgment: opportunities and challenges of LLM-as-a-judge. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 2757\u20132791 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.138"},{"key":"24_CR10","unstructured":"Li, H., et al.: LLMs-as-judges: a comprehensive survey on LLM-based evaluation methods. arXiv preprint: arXiv:2412.05579 (2024)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Li, J., Su, Y.: A map of exploring human interaction patterns with LLM: insights into collaboration and creativity. In: International Conference on Human-Computer Interaction, pp. 60\u201385. Springer (2024)","DOI":"10.1007\/978-3-031-60615-1_5"},{"key":"24_CR12","unstructured":"Liang, Y., Li, J., Yin, J.: A new multi-choice reading comprehension dataset for curriculum learning. In: Asian Conference on Machine Learning, pp. 742\u2013757. PMLR (2019)"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Liu, X., Liu, P., He, H.: An empirical analysis on large language models in debate evaluation. arXiv preprint: arXiv:2406.00050 (2024)","DOI":"10.18653\/v1\/2024.acl-short.44"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Mohammadi, M., Li, Y., Lo, J., Yip, W.: Evaluation and benchmarking of LLM agents: a survey. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, vol. 2, pp. 6129\u20136139 (2025)","DOI":"10.1145\/3711896.3736570"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Moniri, B., Hassani, H., Dobriban, E.: Evaluating the performance of large language models via debates. arXiv preprint: arXiv:2406.11044 (2024)","DOI":"10.18653\/v1\/2025.findings-naacl.109"},{"key":"24_CR16","unstructured":"Ni, S., et\u00a0al.: A survey on large language model benchmarks. arXiv preprint: arXiv:2508.15361 (2025)"},{"key":"24_CR17","unstructured":"Page, M.J., et\u00a0al.: The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 372 (2021)"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Pan, Q., et al.: Human-centered design recommendations for LLM as-a-judge. arXiv preprint: arXiv:2407.03479 (2024)","DOI":"10.18653\/v1\/2024.hucllm-1.2"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Panickssery, A., Bowman, S., Feng, S.: LLM evaluators recognize and favor their own generations. In: Advances in Neural Information Processing Systems, vol. 37, pp. 68772\u201368802 (2024)","DOI":"10.52202\/079017-2197"},{"key":"24_CR20","unstructured":"Peng, J.L., et al.: A survey of useful LLM evaluation. arXiv preprint: arXiv:2406.00936 (2024)"},{"key":"24_CR21","unstructured":"Shi, L., Ma, C., Liang, W., Ma, W., Vosoughi, S.: Judging the judges: a systematic investigation of position bias in pairwise comparative assessments by LLMs (2024)"},{"key":"24_CR22","unstructured":"Srivastava, A., et al.: Beyond the imitation game: quantifying and extrapolating the capabilities of language models. Trans. Mach. Learn. Res. (2023)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Sternlicht, N., Gera, A., Bar-Haim, R., Hope, T., Slonim, N.: Debatable intelligence: benchmarking LLM judges via debate speech evaluation. arXiv preprint: arXiv:2506.05062 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.953"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Zhao, R., Zhang, W., Chia, Y.K., Xu, W., Zhao, D., Bing, L.: Auto-arena: automating LLM evaluations with agent peer battles and committee discussions. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 4440\u20134463 (2025)","DOI":"10.18653\/v1\/2025.acl-long.223"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with mt-bench and chatbot arena. In: Advances in Neural Information Processing Systems, vol. 36, pp. 46595\u201346623 (2023)","DOI":"10.52202\/075280-2020"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in HCI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-30849-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:15:43Z","timestamp":1783520143000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-30849-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032308481","9783032308498"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-30849-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HCII","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montreal, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"hcii2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2026.hci.international\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}