{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T12:32:34Z","timestamp":1776083554079,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730172","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:21:38Z","timestamp":1752456098000},"page":"2637-2641","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Bias in Language Models: Interplay of Architecture and Data?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9771-4142","authenticated-orcid":false,"given":"Mozhgan","family":"Talebpour","sequence":"first","affiliation":[{"name":"University of Essex, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4407-578X","authenticated-orcid":false,"given":"Yunfei","family":"Long","sequence":"additional","affiliation":[{"name":"University of Essex, Colchester, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6509-5325","authenticated-orcid":false,"given":"Alba G.","family":"Seco De Herrera","sequence":"additional","affiliation":[{"name":"National University of Distance Education, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7534-3313","authenticated-orcid":false,"given":"Shoaib","family":"Jameel","sequence":"additional","affiliation":[{"name":"University of Southampton, Southampton, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels. arXiv preprint arXiv:2309.09697","author":"Anantaprayoon Panatchakorn","year":"2023","unstructured":"Panatchakorn Anantaprayoon, Masahiro Kaneko, and Naoaki Okazaki. 2023. Evaluating Gender Bias of Pre-trained Language Models in Natural Language Inference by Considering All Labels. arXiv preprint arXiv:2309.09697 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Probing pre-trained language models for cross-cultural differences in values. arXiv preprint arXiv:2203.13722","author":"Arora Arnav","year":"2022","unstructured":"Arnav Arora, Lucie-Aim\u00e9e Kaffee, and Isabelle Augenstein. 2022. Probing pre-trained language models for cross-cultural differences in values. arXiv preprint arXiv:2203.13722 (2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-021-09881-2"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944937"},{"key":"e_1_3_2_1_5_1","volume-title":"Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems","author":"Bolukbasi Tolga","year":"2016","unstructured":"Tolga Bolukbasi, Kai-Wei Chang, James Y Zou, Venkatesh Saligrama, and Adam T Kalai. 2016. Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_6_1","volume-title":"Measuring and mitigating gender bias in legal contextualized language models. ACM Transactions on Knowledge Discovery from Data","author":"Bozdag Mustafa","year":"2024","unstructured":"Mustafa Bozdag, Nurullah Sevim, and Aykut Ko\u00e7. 2024. Measuring and mitigating gender bias in legal contextualized language models. ACM Transactions on Knowledge Discovery from Data, Vol. 18, 4 (2024), 1-26."},{"key":"e_1_3_2_1_7_1","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang et al. 2023. A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Jacob Cohen. 2013. Statistical power analysis for the behavioral sciences. routledge.","DOI":"10.4324\/9780203771587"},{"key":"e_1_3_2_1_9_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_10_1","first-page":"1","article-title":"Bias of AI-generated content: an examination of news produced by large language models","volume":"14","author":"Fang Xiao","year":"2024","unstructured":"Xiao Fang, Shangkun Che, Minjia Mao, Hongzhe Zhang, Ming Zhao, and Xiaohang Zhao. 2024. Bias of AI-generated content: an examination of news produced by large language models. Scientific Reports, Vol. 14, 1 (2024), 1-20.","journal-title":"Scientific Reports"},{"key":"e_1_3_2_1_11_1","volume-title":"EDBT","author":"Gaci Yacine","year":"2022","unstructured":"Yacine Gaci, Boualem Benatallah, Fabio Casati, and Khalid Benabdeslem. 2022a. Masked Language Models as Stereotype Detectors?. In EDBT 2022."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.651"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580494"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2806416.2806482"},{"key":"e_1_3_2_1_15_1","volume-title":"How large language models encode context knowledge? a layer-wise probing study. arXiv preprint arXiv:2402.16061","author":"Ju Tianjie","year":"2024","unstructured":"Tianjie Ju, Weiwei Sun, Wei Du, Xinwei Yuan, Zhaochun Ren, and Gongshen Liu. 2024. How large language models encode context knowledge? a layer-wise probing study. arXiv preprint arXiv:2402.16061 (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Ctrl: A conditional transformer language model for controllable generation. arXiv preprint arXiv:1909.05858","author":"Keskar Nitish Shirish","year":"2019","unstructured":"Nitish Shirish Keskar, Bryan McCann, Lav R Varshney, Caiming Xiong, and Richard Socher. 2019. Ctrl: A conditional transformer language model for controllable generation. arXiv preprint arXiv:1909.05858 (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"BAD: BiAs Detection for Large Language Models in the context of candidate screening. arXiv preprint arXiv:2305.10407","author":"Koh Nam Ho","year":"2023","unstructured":"Nam Ho Koh, Joseph Plata, and Joyce Chai. 2023. BAD: BiAs Detection for Large Language Models in the context of candidate screening. arXiv preprint arXiv:2305.10407 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Large language models are geographically biased. arXiv preprint arXiv:2402.02680","author":"Manvi Rohin","year":"2024","unstructured":"Rohin Manvi, Samar Khanna, Marshall Burke, David Lobell, and Stefano Ermon. 2024. Large language models are geographically biased. arXiv preprint arXiv:2402.02680 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"A survey on bias and fairness in machine learning. ACM computing surveys (CSUR)","author":"Mehrabi Ninareh","year":"2021","unstructured":"Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021. A survey on bias and fairness in machine learning. ACM computing surveys (CSUR), Vol. 54, 6 (2021), 1-35."},{"key":"e_1_3_2_1_22_1","volume-title":"Nouamane Tazi, Aleksandra Piktus, Sampo Pyysalo, Thomas Wolf, and Colin A Raffel.","author":"Muennighoff Niklas","year":"2024","unstructured":"Niklas Muennighoff, Alexander Rush, Boaz Barak, Teven Le Scao, Nouamane Tazi, Aleksandra Piktus, Sampo Pyysalo, Thomas Wolf, and Colin A Raffel. 2024. Scaling data-constrained language models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Discriminating Systems: Gender, Race and Power in Artificial Intelligence.","author":"West Sarah Myers","year":"2020","unstructured":"Sarah Myers West. 2020. Discriminating Systems: Gender, Race and Power in Artificial Intelligence. (2020)."},{"key":"e_1_3_2_1_24_1","volume-title":"StereoSet: Measuring stereotypical bias in pretrained language models. arXiv preprint arXiv:2004.09456","author":"Nadeem Moin","year":"2020","unstructured":"Moin Nadeem, Anna Bethke, and Siva Reddy. 2020. StereoSet: Measuring stereotypical bias in pretrained language models. arXiv preprint arXiv:2004.09456 (2020)."},{"key":"e_1_3_2_1_25_1","volume-title":"CrowS-pairs: A challenge dataset for measuring social biases in masked language models. arXiv preprint arXiv:2010.00133","author":"Nangia Nikita","year":"2020","unstructured":"Nikita Nangia, Clara Vania, Rasika Bhalerao, and Samuel R Bowman. 2020. CrowS-pairs: A challenge dataset for measuring social biases in masked language models. arXiv preprint arXiv:2010.00133 (2020)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597307"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3020165.3020185"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.563"},{"key":"e_1_3_2_1_29_1","unstructured":"Alec Radford. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_30_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121542"},{"key":"e_1_3_2_1_32_1","unstructured":"Adam Roberts Colin Raffel Katherine Lee Michael Matena Noam Shazeer Peter J Liu Sharan Narang Wei Li and Yanqi Zhou. 2019. Exploring the limits of transfer learning with a unified text-to-text transformer. Google Tech. Rep. (2019)."},{"key":"e_1_3_2_1_33_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Salewski Leonard","year":"2024","unstructured":"Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, and Zeynep Akata. 2024. In-Context Impersonation Reveals Large Language Models' Strengths and Biases. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108","author":"Sanh Victor","year":"2019","unstructured":"Victor Sanh, Lysandre Debut, Julien Chaumond, and Thomas Wolf. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1978942.1979127"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00659"},{"key":"e_1_3_2_1_37_1","volume-title":"Zheda Mai, and Scott Sanner.","author":"Shen Tianshu","year":"2023","unstructured":"Tianshu Shen, Jiaru Li, Mohamed Reda Bouadjenek, Zheda Mai, and Scott Sanner. 2023. Towards understanding and mitigating unintended biases in language model-driven conversational recommendation. Information Processing & Management, Vol. 60, 1 (2023), 103139."},{"key":"e_1_3_2_1_38_1","volume-title":"Fewer errors, but more stereotypes? the effect of model size on gender bias. arXiv preprint arXiv:2206.09860","author":"Tal Yarden","year":"2022","unstructured":"Yarden Tal, Inbal Magar, and Roy Schwartz. 2022. Fewer errors, but more stereotypes? the effect of model size on gender bias. arXiv preprint arXiv:2206.09860 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2966790"},{"key":"e_1_3_2_1_42_1","volume-title":"Measuring and Addressing Indexical Bias in Information Retrieval. arXiv preprint arXiv:2406.04298","author":"Ziems Caleb","year":"2024","unstructured":"Caleb Ziems, William Held, Jane Dwivedi-Yu, and Diyi Yang. 2024. Measuring and Addressing Indexical Bias in Information Retrieval. arXiv preprint arXiv:2406.04298 (2024)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T09:59:48Z","timestamp":1755856788000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730172"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":42,"alternative-id":["10.1145\/3726302.3730172","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730172","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}