{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:19:49Z","timestamp":1784179189684,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,7]]},"DOI":"10.1145\/3767695.3769514","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:14:58Z","timestamp":1764782098000},"page":"64-74","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Developing a Framework for Auditing Large Language Models using Human-in-the-loop"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6142-0637","authenticated-orcid":false,"given":"Maryam","family":"Amirizaniani","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4790-4292","authenticated-orcid":false,"given":"Adrian","family":"Lavergne","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1436-8084","authenticated-orcid":false,"given":"Elizabeth","family":"Snell Okada","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6621-9003","authenticated-orcid":false,"given":"Aman","family":"Chadha","sequence":"additional","affiliation":[{"name":"Stanford University, Palo Alto, CA, USA and Amazon AI, Palo Alto, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1235-3006","authenticated-orcid":false,"given":"Tanya","family":"Roosta","sequence":"additional","affiliation":[{"name":"UC Berkeley, Saratoga, CA, USA and Amazon, Saratoga, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3797-4293","authenticated-orcid":false,"given":"Chirag","family":"Shah","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679222"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642016"},{"key":"e_1_3_2_1_3_1","volume-title":"Ask Me Anything: A simple strategy for prompting language models. arXiv preprint arXiv:2210.02441","author":"Arora Simran","year":"2022","unstructured":"Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, and Christopher R\u00e9. 2022. Ask Me Anything: A simple strategy for prompting language models. arXiv preprint arXiv:2210.02441 (2022)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli.07-034-R2"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334"},{"key":"e_1_3_2_1_6_1","volume-title":"A critical survey of'' bias'' in nlp. arXiv preprint arXiv:2005.14050","author":"Blodgett Su Lin","year":"2020","unstructured":"Su Lin Blodgett, Solon Barocas, and Hal Daum\u00e9 III. 2020. Language (technology) is power: A critical survey of'' bias'' in nlp. arXiv preprint arXiv:2005.14050 (2020)."},{"key":"e_1_3_2_1_7_1","volume-title":"Say It Another Way: Auditing LLMs with a User- Grounded Automated Paraphrasing Framework. arXiv preprint arXiv:2505.03563","author":"Chataigner Cl\u00e9a","year":"2025","unstructured":"Cl\u00e9a Chataigner, Rebecca Ma, Prakhar Ganesh, Afaf Ta\u00efk, Elliot Creager, and Golnoosh Farnadi. 2025. Say It Another Way: Auditing LLMs with a User- Grounded Automated Paraphrasing Framework. arXiv preprint arXiv:2505.03563 (2025)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614905"},{"key":"e_1_3_2_1_9_1","volume-title":"Jason I Hong, Kenneth Holstein, and Motahhare Eslami.","author":"Deng Wesley Hanwen","year":"2025","unstructured":"Wesley Hanwen Deng, Wang Claire, Howard Ziyu Han, Jason I Hong, Kenneth Holstein, and Motahhare Eslami. 2025. WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AI. arXiv preprint arXiv:2501.01397 (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the AAAI Conference on Human Computation and Crowdsourcing","volume":"12","author":"Deng Wesley Hanwen","year":"2024","unstructured":"Wesley Hanwen Deng, Mireia Yurrita, Mark D\u00edaz, Jina Suh, Nick Judd, Lara Groves, Hong Shen, Motahhare Eslami, and Kenneth Holstein. 2024. Responsible Crowdsourcing for Responsible Generative AI: Engaging Crowds in AI Auditing and Evaluation. In Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, Vol. 12. 148--150."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.151"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713477"},{"key":"e_1_3_2_1_13_1","volume-title":"Eugene Jang, and Jonathan","author":"Felkner Virginia K.","year":"2022","unstructured":"Virginia K. Felkner, Ho-Chun Herbert Chang, Eugene Jang, and Jonathan May. 2022. Towards WinoQueer: Developing a benchmark for anti-queer bias in large language models. arXiv preprint arXiv:2206.11484 (2022)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.accinf.2025.100748"},{"key":"e_1_3_2_1_15_1","volume-title":"On the Role of Prompt Multiplicity in LLM Hallucination Evaluation. In ICLR 2025 Workshop on Building Trust in Language Models and Applications. https:\/\/openreview.net\/forum?id=yr0QEDDTSO","author":"Ganesh Prakhar","year":"2025","unstructured":"Prakhar Ganesh, Reza Shokri, and Golnoosh Farnadi. 2025. On the Role of Prompt Multiplicity in LLM Hallucination Evaluation. In ICLR 2025 Workshop on Building Trust in Language Models and Applications. https:\/\/openreview.net\/forum?id=yr0QEDDTSO"},{"key":"e_1_3_2_1_16_1","volume-title":"ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages. arXiv preprint arXiv:2305.10510","author":"Ghosh Sourojit","year":"2023","unstructured":"Sourojit Ghosh and Aylin Caliskan. 2023. ChatGPT Perpetuates Gender Bias in Machine Translation and Ignores Non-Gendered Pronouns: Findings across Bengali and Five other Low-Resource Languages. arXiv preprint arXiv:2305.10510 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Political Bias in Large Language Models. The Commons: Puget Sound Journal of Politics 4","author":"Gover Lucas","year":"2023","unstructured":"Lucas Gover. 2023. Political Bias in Large Language Models. The Commons: Puget Sound Journal of Politics 4 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers. arXiv preprint arXiv:2309.08532","author":"Guo Qingyan","year":"2023","unstructured":"Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, and Yujiu Yang. 2023. Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers. arXiv preprint arXiv:2309.08532 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"The political ideology of conversational AI: Converging evidence on ChatGPT's proenvironmental, left-libertarian orientation. arXiv preprint arXiv:2301.01768","author":"Hartmann Jochen","year":"2023","unstructured":"Jochen Hartmann, Jasper Schwenzow, and Maximilian Witte. 2023. The political ideology of conversational AI: Converging evidence on ChatGPT's proenvironmental, left-libertarian orientation. arXiv preprint arXiv:2301.01768 (2023)."},{"key":"e_1_3_2_1_20_1","volume-title":"Felipe Vieira Frujeri, and Ida Momennejad","author":"Hasanbeig Hosein","year":"2023","unstructured":"Hosein Hasanbeig, Hiteshi Sharma, Leo Betthauser, Felipe Vieira Frujeri, and Ida Momennejad. 2023. ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning. arXiv e-prints (2023), arXiv--2309."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.741"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_1_23_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_24_1","unstructured":"Omar Khattab Arnav Singhvi Paridhi Maheshwari Zhiyuan Zhang Keshav Santhanam Saiful Haq Ashutosh Sharma Thomas T Joshi Hanna Moazam Heather Miller et al. 2023. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines. In R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation Models."},{"key":"e_1_3_2_1_25_1","unstructured":"Klaus Krippendorff. 2011. Computing Krippendorff's alpha-reliability. (2011)."},{"key":"e_1_3_2_1_26_1","volume-title":"Content analysis: An introduction to its methodology","author":"Krippendorff Klaus","unstructured":"Klaus Krippendorff. 2018. Content analysis: An introduction to its methodology. Sage publications."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acllong"},{"key":"e_1_3_2_1_28_1","volume-title":"ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, Barcelona, Spain, 74--81. https:\/\/aclanthology.org\/W04--1013"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.324"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acllong"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-024-01847-2"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"39","author":"Ling Lin","year":"2025","unstructured":"Lin Ling, Fazle Rabbi, Song Wang, and Jinqiu Yang. 2025. Bias unveiled: Investigating social bias in LLM-Generated Code. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39. 27491--27499."},{"key":"e_1_3_2_1_33_1","volume-title":"Truthfulness in Large Language Models","author":"Liu Kevin","unstructured":"Kevin Liu. 2023. Truthfulness in Large Language Models. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science. https:\/\/hdl.handle.net\/1721.1\/151345"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence 35","author":"Liu Ruibo","year":"2021","unstructured":"Ruibo Liu, Chenyan Jia, Jason Wei, Guangxuan Xu, Lili Wang, and Soroush Vosoughi. 2021. Mitigating political bias in language models through reinforced calibration. In Proceedings of the AAAI Conference on Artificial Intelligence 35 (2021), 14857--14866."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3706729"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.31"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.16073"},{"key":"e_1_3_2_1_39_1","volume-title":"Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models. In ICML 2025 Workshop on Reliable and Responsible Foundation Models. https:\/\/openreview.net\/forum?id=m6f95cqQx2","author":"Rossi Lorenzo","year":"2025","unstructured":"Bart?omiej Marek, Lorenzo Rossi, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch, and Adam Dziedzic. 2025. Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models. In ICML 2025 Workshop on Reliable and Responsible Foundation Models. https:\/\/openreview.net\/forum?id=m6f95cqQx2"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"crossref","unstructured":"Robert W. McGee. 2023. Is chat gpt biased against conservatives? an empirical study. An Empirical Study. (2023).","DOI":"10.2139\/ssrn.4359405"},{"key":"e_1_3_2_1_41_1","volume-title":"Hannah Rose Kirk, and Luciano Floridi","author":"M\u00f6kander Jakob","year":"2023","unstructured":"Jakob M\u00f6kander, Jonas Schuett, Hannah Rose Kirk, and Luciano Floridi. 2023. Auditing large language models: a three-layered approach. arXiv preprint arXiv:2302.08500 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43681-023-00289-2"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11127-023-01097--2"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"key":"e_1_3_2_1_46_1","volume-title":"The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116","author":"Penedo Guilherme","year":"2023","unstructured":"Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116 (2023)."},{"key":"e_1_3_2_1_47_1","unstructured":"Vatsal Raina and Mark Gales. 2022. Multiple-Choice Question Generation: Towards an Automated Assessment Framework. arXiv:2209.11830 [cs.CL]"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604712"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2309.11064"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.230"},{"key":"e_1_3_2_1_51_1","volume-title":"The Self-Perception and Political Biases of ChatGPT. arXiv preprint arXiv:2304.07333","author":"Rutinowski J\u00e9r\u00f4me","year":"2023","unstructured":"J\u00e9r\u00f4me Rutinowski, Sven Franke, Jan Endendyk, Ina Dormuth, and Markus Pauly. 2023. The Self-Perception and Political Biases of ChatGPT. arXiv preprint arXiv:2304.07333 (2023)."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.59"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445518"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3709599"},{"key":"e_1_3_2_1_55_1","volume-title":"Joon Sung Park, and Diyi Yang.","author":"Shen Hong","year":"2023","unstructured":"Hong Shen, Tianshi Li, Toby Jia-Jun Li, Joon Sung Park, and Diyi Yang. 2023. Shaping the Emerging Norms of Using Large Language Models in Social Computing Research. In Companion Publication of the 2023 Conference on Computer Supported Cooperative Work and Social Computing. 569--571."},{"key":"e_1_3_2_1_56_1","unstructured":"Xinyue Shen Zeyuan Chen Michael Backes and Yang Zhang. 2023. In chatgpt we trust? measuring and characterizing the reliability of chatgpt. arXiv preprint arXiv:2304.08979 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"CHEN ZHAO, SHI FENG, HAL DAUM\u00c9 III, and JORDAN BOYD-GRABER.","author":"CHENGLEI SI, NAVITA","year":"2023","unstructured":"CHENGLEI SI, NAVITA GOYAL, SHERRY TONGSHUANG WU, CHEN ZHAO, SHI FENG, HAL DAUM\u00c9 III, and JORDAN BOYD-GRABER. 2023. Large Language Models Help Humans Verify Truthfulness--Except When They Are Convincingly Wrong. arXiv preprint arXiv:2310.12558 (2023)."},{"key":"e_1_3_2_1_58_1","volume-title":"Audit-llm: Multi-agent collaboration for log-based insider threat detection. arXiv preprint arXiv:2408.08902","author":"Song Chengyu","year":"2024","unstructured":"Chengyu Song, Linru Ma, Jianming Zheng, Jinzhi Liao, Hongyu Kuang, and Lin Yang. 2024. Audit-llm: Multi-agent collaboration for log-based insider threat detection. arXiv preprint arXiv:2408.08902 (2024)."},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of BigScience Episode 5--Workshop on Challenges & Perspectives in Creating Large Language Models","author":"Talat Zeerak","year":"2022","unstructured":"Zeerak Talat, Aur\u00e9lie N\u00e9v\u00e9ol, Stella Biderman, Miruna Clinciu, Manan Dey, Shayne Longpre, Sasha Luccioni, Maraim Masoud, Margaret Mitchell, Dragomir Radev, Shanya Sharma, Arjun Subramonian, Jaesung Tae, Samson Tan, Deepak Tunuguntla, and Oskar Van Der Wal. 2022. You reap what you sow: On the challenges of bias evaluation under multilingual settings. In Proceedings of BigScience Episode 5--Workshop on Challenges & Perspectives in Creating Large Language Models (2022)."},{"key":"e_1_3_2_1_60_1","volume-title":"Unveiling gender bias in terms of profession across LLMs: Analyzing and addressing sociological implications. arXiv preprint arXiv:2307.09162","author":"Thakur Vishesh","year":"2023","unstructured":"Vishesh Thakur. 2023. Unveiling gender bias in terms of profession across LLMs: Analyzing and addressing sociological implications. arXiv preprint arXiv:2307.09162 (2023)."},{"key":"e_1_3_2_1_61_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian CantonFerrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian XiangKuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_62_1","volume-title":"She Elicits Requirements and He Tests: Software Engineering Gender Bias in Large Language Models. arXiv preprint arXiv:2303.10131","author":"Treude Christoph","year":"2023","unstructured":"Christoph Treude and Hideaki Hata. 2023. She Elicits Requirements and He Tests: Software Engineering Gender Bias in Large Language Models. arXiv preprint arXiv:2303.10131 (2023)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642335"},{"key":"e_1_3_2_1_64_1","volume-title":"Auditgpt: Auditing smart contracts with chatgpt. arXiv preprint arXiv:2404.04306","author":"Xia Shihao","year":"2024","unstructured":"Shihao Xia, Shuai Shao, Mengting He, Tingting Yu, Linhai Song, and Yiying Zhang. 2024. Auditgpt: Auditing smart contracts with chatgpt. arXiv preprint arXiv:2404.04306 (2024)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3636302"},{"key":"e_1_3_2_1_66_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"37","author":"Yang Ke","year":"2023","unstructured":"Ke Yang, Charles Yu, Yi R Fung, Manling Li, and Heng Ji. 2023. Adept: A debiasing prompt framework. In Proceedings of the AAAI conference on artificial intelligence, Vol. 37. 10780--10788."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.256"},{"key":"e_1_3_2_1_68_1","volume-title":"Users Track, Masaru Yamada and Felix do Carmo (Eds.)","author":"Yang Xinyi","year":"2023","unstructured":"Xinyi Yang, Runzhe Zhan, Derek F. Wong, Junchao Wu, and Lidia S. Chao. 2023. Human-in-the-loop Machine Translation with Large Language Model. In Proceedings of Machine Translation Summit XIX, Vol. 2: Users Track, Masaru Yamada and Felix do Carmo (Eds.). Asia-Pacific Association for Machine Translation, Macau SAR, China, 88--98. https:\/\/aclanthology.org\/2023.mtsummit-users.8"},{"key":"e_1_3_2_1_69_1","volume-title":"Healthcare","volume":"11","author":"Yu Ping","year":"2023","unstructured":"Ping Yu, Hua Xu, Xia Hu, and Chao Deng. 2023. Leveraging Generative AI and Large Language Models: A Comprehensive Roadmap for Healthcare Integration. In Healthcare, Vol. 11. MDPI, 2776."},{"key":"e_1_3_2_1_70_1","volume-title":"Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675","author":"Zhang Tianyi","year":"2019","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-demo.1"}],"event":{"name":"SIGIR-AP 2025:Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region","location":"Xi'an China","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2025 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region"],"original-title":[],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:19:34Z","timestamp":1764782374000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767695.3769514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":71,"alternative-id":["10.1145\/3767695.3769514","10.1145\/3767695"],"URL":"https:\/\/doi.org\/10.1145\/3767695.3769514","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}