{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T05:40:09Z","timestamp":1750657209262,"version":"3.41.0"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031962349","type":"print"},{"value":"9783031962356","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-96235-6_30","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T05:03:20Z","timestamp":1750655000000},"page":"417-430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward Safer and\u00a0Trustworthy Chatbots in\u00a0E-Commerce: An LLM-as-a-Judge Approach for\u00a0Ethical Evaluation"],"prefix":"10.1007","author":[{"given":"Tam\u00e1s","family":"Janusko","sequence":"first","affiliation":[]},{"given":"Ricardo","family":"Bochnia","sequence":"additional","affiliation":[]},{"given":"Moritz","family":"Harnisch","sequence":"additional","affiliation":[]},{"given":"Anna-Magdalena","family":"Krau\u00df","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Richter","sequence":"additional","affiliation":[]},{"given":"Gunnar","family":"Hempel","sequence":"additional","affiliation":[]},{"given":"Steffen","family":"Tomschke","sequence":"additional","affiliation":[]},{"given":"J\u00fcrgen","family":"Anke","sequence":"additional","affiliation":[]},{"given":"Maik","family":"Thiele","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"30_CR1","unstructured":"Bedemariam, R., et al.: Potential and perils of large language models as judges of unstructured textual data (2025)"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Caselli, T., Basile, V., Mitrovi\u0107, J., Granitzer, M.: HateBERT: retraining BERT for abusive language detection in English. In: Mostafazadeh\u00a0Davani, A., Kiela, D., Lambert, M., Vidgen, B., Prabhakaran, V., and Waseem, Z., (eds.) Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), pp. 17\u201325 (2021). Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.woah-1.3"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Demus, C., Pitz, J., Sch\u00fctz, M., Probol, N., Siegel, M., Labudde, D.: Detox: a comprehensive dataset for German offensive language and conversation analysis. In: Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH), pp. 143\u2013153, Seattle, Washington (Hybrid) (2022). Association for Computational Linguistics","DOI":"10.18653\/v1\/2022.woah-1.14"},{"key":"30_CR4","unstructured":"Deshpande, D., Ravi, S.S., CH-Wang, S., Mielczarek, B., Kannappan, A., Qian, R.: Glider: Grading LLM interactions and decisions using explainable ranking (2024)"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Fan, Z., Wang, W., W, X., and Zhang, D.: SedarEval: automated evaluation using self-adaptive rubrics. In: Al-Onaizan, Y., Bansal, M., Chen, Y.-N., (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 16916\u201316930, Miami, Florida, USA (2024). Association for Computational Linguistics","DOI":"10.18653\/v1\/2024.findings-emnlp.984"},{"key":"30_CR6","unstructured":"Gera, A., Boni, O., Perlitz, Y., Bar-Haim, R., Eden, L., Yehudai, A.: JuStRank: benchmarking LLM judges for system ranking (2024)"},{"key":"30_CR7","unstructured":"Hanu, L., Unitary team. Detoxify. Github (2020). https:\/\/github.com\/unitaryai\/detoxify"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Hartvigsen, T., Gabriel, S., Palangi, H., Sap, M., Ray, D., Kamar, E.: ToxiGen: a large-scale machine-generated dataset for adversarial and implicit hate speech detection (2022)","DOI":"10.18653\/v1\/2022.acl-long.234"},{"key":"30_CR9","unstructured":"Hu, Z., Zhang, J., Xiong, Z., Ratner, A., Xiong, H., Krishna, R.: Language model preference evaluation with multiple weak evaluators (2024)"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Kim, S., et al.: Prometheus 2: an open source language model specialized in evaluating other language models (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.248"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Lee, D., Hwang, Y., Kim, Y., Park, J., Jung, K.: Are LLM-judges robust to expressions of uncertainty? Investigating the effect of epistemic markers on LLM-based evaluation (2024)","DOI":"10.18653\/v1\/2025.naacl-long.452"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., Iter, D., Xu, Y., Wang, S., Xu, R., and Zhu, C.: G-Eval: NLG evaluation using GPT-4 with better human alignment (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Szymanski, A., Ziems, N., Eicher-Miller, H.A., Li, T.J.-J., Jiang, M., Metoyer, R.A.: Limitations of the LLM-as-a-judge approach for evaluating LLM outputs in expert knowledge tasks (2024)","DOI":"10.1145\/3708359.3712091"},{"key":"30_CR14","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena (2023)"}],"container-title":["IFIP Advances in Information and Communication Technology","Artificial Intelligence Applications and Innovations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-96235-6_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T05:03:26Z","timestamp":1750655006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-96235-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031962349","9783031962356"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-96235-6_30","relation":{},"ISSN":["1868-4238","1868-422X"],"issn-type":[{"value":"1868-4238","type":"print"},{"value":"1868-422X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Artificial Intelligence Applications and Innovations","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ifipaiai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}