{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T19:56:49Z","timestamp":1774295809142,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3715275.3732182","type":"proceedings-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:03:13Z","timestamp":1750698193000},"page":"2815-2846","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3876-0094","authenticated-orcid":false,"given":"Hanjia","family":"Lyu","sequence":"first","affiliation":[{"name":"University of Rochester, Rochester, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3902-7131","authenticated-orcid":false,"given":"Jian","family":"Kang","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6233-8256","authenticated-orcid":false,"given":"Allison","family":"Koenecke","sequence":"additional","affiliation":[{"name":"Cornell University, Ithaca, New York, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2018. Name Statistics. https:\/\/www.ris.gov.tw\/documents\/data\/5\/2\/107namestat.pdf Accessed: 04-09-2024."},{"key":"e_1_3_3_2_3_2","volume-title":"AAAI Conference on Artificial Intelligence","author":"Acharya Anurag","year":"2021","unstructured":"Anurag Acharya, Kartik Talamadupula, and Mark\u00a0A Finlayson. 2021. An atlas of cultural commonsense for machine reasoning. In AAAI Conference on Artificial Intelligence."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.614"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Ai2. 2021. c4. https:\/\/huggingface.co\/datasets\/allenai\/c4. Accessed: 2025-04-28.","DOI":"10.1109\/MWC.2021.9490600"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Mohammad Atari Mona\u00a0J Xue Peter\u00a0S Park Dami\u00e1n Blasi and Joseph Henrich. 2023. Which humans? (2023).","DOI":"10.31234\/osf.io\/5b26t"},{"key":"e_1_3_3_2_7_2","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et\u00a0al. 2023. Qwen technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.16609 (2023)."},{"key":"e_1_3_3_2_8_2","volume-title":"Fairness and Machine Learning: Limitations and Opportunities","author":"Barocas Solon","year":"2023","unstructured":"Solon Barocas, Moritz Hardt, and Arvind Narayanan. 2023. Fairness and Machine Learning: Limitations and Opportunities. MIT Press."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.414"},{"key":"e_1_3_3_2_10_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_11_2","unstructured":"Jianbin Chang. 2023. chinese-c4. https:\/\/huggingface.co\/datasets\/shjwudp\/chinese-c4. Accessed: 2025-04-28."},{"key":"e_1_3_3_2_12_2","unstructured":"Pokai Chang. 2023. zh-tw-wikipedia. https:\/\/huggingface.co\/datasets\/zetavg\/zh-tw-wikipedia. Accessed: 2025-04-28."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Jacob Cohen. 1992. Statistical power analysis. Current directions in psychological science 1(3) (1992).","DOI":"10.1111\/1467-8721.ep10768783"},{"key":"e_1_3_3_2_14_2","unstructured":"Zhengxiao Du Yujie Qian Xiao Liu Ming Ding Jiezhong Qiu Zhilin Yang and Jie Tang. 2022. GLM: General Language Model Pretraining with Autoregressive Blank Infilling. (2022) 320\u2013335."},{"key":"e_1_3_3_2_15_2","unstructured":"Philipp Ennen Po-Chun Hsu Chan-Jan Hsu Chang-Le Liu Yen-Chen Wu Yin-Hsiang Liao Chin-Tung Lin Da-Shan Shiu and Wei-Yun Ma. 2023. Extending the pre-training of bloom for improved support of traditional chinese: Models methods and results. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.04715 (2023)."},{"key":"e_1_3_3_2_16_2","unstructured":"Chengguang Gan Qinghao Zhang and Tatsunori Mori. 2024. Application of llm agents in recruitment: A novel framework for resume screening. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.08315 (2024)."},{"key":"e_1_3_3_2_17_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et\u00a0al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.12948 (2025)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.kallm-1.7"},{"key":"e_1_3_3_2_19_2","unstructured":"Valentin Hofmann Pratyusha\u00a0Ria Kalluri Dan Jurafsky and Sharese King. 2024. Dialect prejudice predicts AI decisions about people\u2019s character employability and criminality. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.00742 (2024)."},{"key":"e_1_3_3_2_20_2","unstructured":"Chan-Jan Hsu Chang-Le Liu Feng-Ting Liao Po-Chun Hsu Yi-Chang Chen and Da-shan Shiu. 2023. Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.08448 (2023)."},{"key":"e_1_3_3_2_21_2","unstructured":"Chan-Jan Hsu Chang-Le Liu Feng-Ting Liao Po-Chun Hsu Yi-Chang Chen and Da-Shan Shiu. 2024. Breeze-7B Technical Report. (2024). arxiv:https:\/\/arXiv.org\/abs\/2403.02712\u00a0[cs.CL]"},{"key":"e_1_3_3_2_22_2","unstructured":"Yuzhen Huang Yuzhuo Bai Zhihao Zhu Junlei Zhang Jinghan Zhang Tangjun Su Junteng Liu Chuancheng Lv Yikai Zhang Yao Fu et\u00a0al. 2024. C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_23_2","unstructured":"Lee\u00a0Chak Kei. 2023. OpenOrca-Traditional-Chinese. https:\/\/huggingface.co\/datasets\/lchakkei\/OpenOrca-Traditional-Chinese. Accessed: 2025-04-28."},{"key":"e_1_3_3_2_24_2","unstructured":"Haonan Li Yixuan Zhang Fajri Koto Yifei Yang Hai Zhao Yeyun Gong Nan Duan and Timothy Baldwin. 2023. Cmmlu: Measuring massive multitask language understanding in chinese. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.09212 (2023)."},{"key":"e_1_3_3_2_25_2","unstructured":"Sheng-Wei Li. 2024. c4-zhtw. https:\/\/huggingface.co\/datasets\/liswei\/c4-zhtw. Accessed: 2025-04-28."},{"key":"e_1_3_3_2_26_2","unstructured":"Sheng-Wei Li. 2024. common-crawl-zhtw. https:\/\/huggingface.co\/datasets\/liswei\/common-crawl-zhtw. Accessed: 2025-04-28."},{"key":"e_1_3_3_2_27_2","volume-title":"Cross-Strait Common Vocabulary","author":"Li Xingjian","year":"2014","unstructured":"Xingjian Li, Zhiqun Qiu, and Fuling Xu. 2014. Cross-Strait Common Vocabulary. Fujian People\u2019s Publishing House."},{"key":"e_1_3_3_2_28_2","unstructured":"Yizhi Li. 2024. MAP-CC. https:\/\/huggingface.co\/datasets\/m-a-p\/MAP-CC. Accessed: 2025-04-28."},{"key":"e_1_3_3_2_29_2","unstructured":"Yen-Ting Lin. 2024. TaiwanChat. https:\/\/huggingface.co\/datasets\/yentinglin\/TaiwanChat. Accessed: 2025-04-28."},{"key":"e_1_3_3_2_30_2","unstructured":"Yen-Ting Lin and Yun-Nung Chen. 2023. Taiwan llm: Bridging the linguistic divide with a culturally aligned language model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.17487 (2023)."},{"key":"e_1_3_3_2_31_2","unstructured":"Chuang Liu Renren Jin Yuqi Ren Linhao Yu Tianyu Dong Xiaohan Peng Shuting Zhang Jianxiang Peng Peiyi Zhang Qingqing Lyu et\u00a0al. 2023. M3ke: A massive multi-level multi-subject knowledge evaluation benchmark for chinese large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.10263 (2023)."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1167\/12.9.533"},{"key":"e_1_3_3_2_33_2","unstructured":"Xiao Liu Xuanyu Lei Shengyuan Wang Yue Huang Zhuoer Feng Bosi Wen Jiale Cheng Pei Ke Yifan Xu Weng\u00a0Lam Tam et\u00a0al. 2023. Alignbench: Benchmarking chinese alignment of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.18743 (2023)."},{"key":"e_1_3_3_2_34_2","unstructured":"Mapull. 2022. Chinese Pinyin Dictionary. https:\/\/github.com\/mapull\/chinese-dictionary Accessed: 04-09-2024."},{"key":"e_1_3_3_2_35_2","unstructured":"AI Meta. 2024. Introducing meta llama 3: The most capable openly available llm to date. Meta AI. (2024)."},{"key":"e_1_3_3_2_36_2","unstructured":"Marco Monroy. 2024. Simplified vs. Traditional Chinese: What\u2019s the difference? A guide. https:\/\/www.berlitz.com\/blog\/traditional-vs-simplified-chinese Accessed: 06-15-2024."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"e_1_3_3_2_38_2","unstructured":"New York City Council. 2021. Local Law 144 of 2021. https:\/\/www.nyc.gov\/assets\/dca\/downloads\/pdf\/about\/Local-Law-144.pdf."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.413"},{"key":"e_1_3_3_2_40_2","unstructured":"Ministry of Public Security\u00a0(China). 2013. Moat Popular Names. https:\/\/web.archive.org\/web\/20160920191749http:\/\/zhaoren.idtag.cn\/samename\/searchName!pmbyrepeatlist.htm Accessed: 04-09-2024."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR abs\/2303.08774 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.08774 arXiv:https:\/\/arXiv.org\/abs\/2303.08774","DOI":"10.48550\/ARXIV.2303.08774"},{"key":"e_1_3_3_2_42_2","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/ Accessed: 06-12-2024."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.113"},{"key":"e_1_3_3_2_44_2","unstructured":"Weihong Qi Hanjia Lyu and Jiebo Luo. 2024. Representation bias in political sample simulations with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.11409 (2024)."},{"key":"e_1_3_3_2_45_2","unstructured":"Science & Technology\u00a0Policy Research and Information Center. 2020. Formosa Language Understanding Dataset. https:\/\/scidm.nchc.org.tw\/dataset\/grandchallenge2020 Accessed: 06-12-2024."},{"key":"e_1_3_3_2_46_2","first-page":"1","volume-title":"2024 Fourth International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT)","author":"Rithani M","year":"2024","unstructured":"M Rithani, R Venkatakrishnan, et\u00a0al. 2024. Empirical Evaluation of Large Language Models in Resume Classification. In 2024 Fourth International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT). IEEE, 1\u20134."},{"key":"e_1_3_3_2_47_2","unstructured":"Chih\u00a0Chieh Shao Trois Liu Yuting Lai Yiying Tseng and Sam Tsai. 2018. DRCD: A Chinese machine reading comprehension dataset. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1806.00920 (2018)."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Siqi Shen Lajanugen Logeswaran Moontae Lee Honglak Lee Soujanya Poria and Rada Mihalcea. 2024. Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.04655 (2024).","DOI":"10.18653\/v1\/2024.naacl-long.316"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Chenglei Si Zhengyan Zhang Yingfa Chen Fanchao Qi Xiaozhi Wang Zhiyuan Liu Yasheng Wang Qun Liu and Maosong Sun. 2023. Sub-Character Tokenization for Chinese Pretrained Language Models. Transactions of the Association for Computational Linguistics 11 (2023) 469\u2013487. https:\/\/doi.org\/10.1162\/tacla00560","DOI":"10.1162\/tacla00560"},{"key":"e_1_3_3_2_50_2","unstructured":"Zhi-Rui Tam Ya-Ting Pai Yen-Wei Lee Jun-Da Chen Wei-Min Chu Sega Cheng and Hong-Han Shuai. 2024. An improved traditional chinese evaluation suite for foundation model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.01858 (2024)."},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"David Thissen Lynne Steinberg and Daniel Kuang. 2002. Quick and easy implementation of the Benjamini-Hochberg procedure for controlling the false positive rate in multiple comparisons. Journal of educational and behavioral statistics 27 1 (2002) 77\u201383.","DOI":"10.3102\/10769986027001077"},{"key":"e_1_3_3_2_52_2","first-page":"352","volume-title":"International Conference on Future Data and Security Engineering","author":"Tran Thanh\u00a0Tung","year":"2023","unstructured":"Thanh\u00a0Tung Tran, Truong\u00a0Giang Nguyen, Thai\u00a0Hoa Dang, and Yuta Yoshinaga. 2023. Improving Human Resources\u2019 Efficiency with a Generative AI-Based Resume Analysis Solution. In International Conference on Future Data and Security Engineering. Springer, 352\u2013365."},{"key":"e_1_3_3_2_53_2","unstructured":"Dixuan Wang Yanda Li Junyuan Jiang Zepeng Ding Guochao Jiang Jiaqing Liang and Deqing Yang. 2024. Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.17067 (2024)."},{"key":"e_1_3_3_2_54_2","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et\u00a0al. 2022. Emergent abilities of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2206.07682 (2022)."},{"key":"e_1_3_3_2_55_2","unstructured":"Liang Xu Anqi Li Lei Zhu Hang Xue Changtai Zhu Kangkang Zhao Haonan He Xuanwei Zhang Qiyue Kang and Zhenzhong Lan. 2023. Superclue: A comprehensive chinese large language model benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.15020 (2023)."},{"key":"e_1_3_3_2_56_2","unstructured":"Qinyang Xu. 2023. BaiduBaike-5.63M. https:\/\/huggingface.co\/datasets\/xuqinyang\/BaiduBaike-5.63M. Accessed: 2025-04-28."},{"key":"e_1_3_3_2_57_2","unstructured":"Aiyuan Yang Bin Xiao Bingning Wang Borong Zhang Ce Bian Chao Yin Chenxu Lv Da Pan Dian Wang Dong Yan et\u00a0al. 2023. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.10305 (2023)."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"crossref","unstructured":"Ruoxiao Yang and William Shi\u00a0Yuan Wang. 2018. Categorical perception of Chinese characters by simplified and traditional Chinese readers. Reading and Writing 31 (2018) 1133\u20131154.","DOI":"10.1007\/s11145-018-9832-y"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.132"},{"key":"e_1_3_3_2_60_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zeng Aohan","year":"2023","unstructured":"Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, et\u00a0al. 2023. GLM-130B: An Open Bilingual Pre-trained Model. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_2_61_2","unstructured":"Hui Zeng. 2023. Measuring massive multitask chinese understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.12986 (2023)."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.491"},{"key":"e_1_3_3_2_63_2","first-page":"80","volume-title":"Proceedings of the Ancient Language Processing Workshop","author":"Zhang Yixuan","year":"2023","unstructured":"Yixuan Zhang and Haonan Li. 2023. Can Large Language Model Comprehend Ancient Chinese? A Preliminary Test on ACLUE. In Proceedings of the Ancient Language Processing Workshop, Adam Anderson, Shai Gordin, Bin Li, Yudong Liu, and Marco\u00a0C. Passarotti (Eds.). INCOMA Ltd., Shoumen, Bulgaria, Varna, Bulgaria, 80\u201387. https:\/\/aclanthology.org\/2023.alp-1.9\/"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2003"},{"key":"e_1_3_3_2_65_2","unstructured":"Wayne\u00a0Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et\u00a0al. 2023. A survey of large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.18223 (2023)."},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"crossref","unstructured":"Wanjun Zhong Ruixiang Cui Yiduo Guo Yaobo Liang Shuai Lu Yanlin Wang Amin Saied Weizhu Chen and Nan Duan. 2023. Agieval: A human-centric benchmark for evaluating foundation models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.06364 (2023).","DOI":"10.18653\/v1\/2024.findings-naacl.149"}],"event":{"name":"FAccT '25: The 2025 ACM Conference on Fairness, Accountability, and Transparency","location":"Athens Greece","acronym":"FAccT '25"},"container-title":["Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3715275.3732182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T11:16:53Z","timestamp":1750763813000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715275.3732182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":65,"alternative-id":["10.1145\/3715275.3732182","10.1145\/3715275"],"URL":"https:\/\/doi.org\/10.1145\/3715275.3732182","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-06-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}