{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T07:01:17Z","timestamp":1781334077601,"version":"3.54.1"},"reference-count":100,"publisher":"Association for Computing Machinery (ACM)","issue":"ISSTA","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. ACM Softw. Eng."],"published-print":{"date-parts":[[2025,6,22]]},"abstract":"<jats:p>Large Language Models (LLMs) have demonstrated remarkable performance across diverse applications, yet they inadvertently absorb spurious correlations from training data, leading to stereotype associations between biased concepts and specific social groups. These associations perpetuate and even amplify harmful social biases, raising significant concerns about fairness, which is a crucial issue in software engineering. To mitigate such biases, prior studies have attempted to project model embeddings into unbiased spaces during inference. However, these approaches have shown limited effectiveness due to their weak alignment with downstream social biases. Inspired by the observation that concept cognition in LLMs is primarily represented through a linear associative memory mechanism, where key-value mapping occurs in the MLP layers, we posited that biased concepts and social groups are similarly encoded as entity (key) and information (value) pairs, which can be manipulated to promote fairer associations. To this end, we propose Fairness Mediator (FairMed), an effective and efficient bias mitigation framework that neutralizes stereotype associations. Our framework comprises two main components: a stereotype association prober and an adversarial debiasing neutralizer. The prober captures stereotype associations encoded within MLP layer activations by employing prompts centered around biased concepts (keys) to detect the emission probabilities for social groups (values). Subsequently, the adversarial debiasing neutralizer intervenes in MLP activations during inference to equalize the association probabilities among different social groups. Extensive experiments across nine protected attributes show that our FairMed significantly outperforms state-of-the-art methods in effectiveness, achieving average bias reductions of up to 84.42<\/jats:p>","DOI":"10.1145\/3728881","type":"journal-article","created":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T10:52:56Z","timestamp":1750589576000},"page":"250-273","source":"Crossref","is-referenced-by-count":5,"title":["Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models"],"prefix":"10.1145","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8227-0052","authenticated-orcid":false,"given":"Yisong","family":"Xiao","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4224-1318","authenticated-orcid":false,"given":"Aishan","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6154-0233","authenticated-orcid":false,"given":"Siyuan","family":"Liang","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7618-3275","authenticated-orcid":false,"given":"Xianglong","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"},{"name":"Zhongguancun Laboratory, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,22]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2017. The adult census income dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/adult"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"e_1_2_1_3_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, and Shyamal Anadkat.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, and Shyamal Anadkat. 2023. Gpt-4 technical report. arXiv:2303.08774."},{"key":"e_1_2_1_4_1","volume-title":"A simple neural network generating an interactive memory. Mathematical biosciences, 14, 3-4","author":"Anderson James A","year":"1972","unstructured":"James A Anderson. 1972. A simple neural network generating an interactive memory. Mathematical biosciences, 14, 3-4 (1972), 197\u2013220."},{"key":"e_1_2_1_5_1","unstructured":"Rohan Anil Andrew M Dai Orhan Firat Melvin Johnson Dmitry Lepikhin Alexandre Passos Siamak Shakeri Emanuel Taropa Paige Bailey and Zhifeng Chen. 2023. Palm 2 technical report. arXiv:2305.10403."},{"key":"e_1_2_1_6_1","unstructured":"Anonym. 2024. Fairness Mediator. https:\/\/sites.google.com\/view\/fairness-mediator\/home"},{"key":"e_1_2_1_7_1","first-page":"5087","article-title":"Biasfinder: Metamorphic test generation to uncover bias for sentiment analysis systems","volume":"48","author":"Asyrofi Muhammad Hilmi","year":"2021","unstructured":"Muhammad Hilmi Asyrofi, Zhou Yang, Imam Nur Bani Yusuf, Hong Jin Kang, Ferdian Thung, and David Lo. 2021. Biasfinder: Metamorphic test generation to uncover bias for sentiment analysis systems. IEEE Transactions on Software Engineering, 48, 12 (2021), 5087\u20135101.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_2_1_8_1","unstructured":"Newsbeat BBC. 2019. Taylor Swift \u2019tried to sue\u2019 Microsoft over racist chatbot Tay.. https:\/\/www.bbc.com\/news\/newsbeat-49645508"},{"key":"e_1_2_1_9_1","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1177\/0146167213520458","article-title":"Stereotype associations and emotion recognition","volume":"40","author":"Bijlstra Gijsbert","year":"2014","unstructured":"Gijsbert Bijlstra, Rob W Holland, Ron Dotsch, Kurt Hugenberg, and Daniel HJ Wigboldus. 2014. Stereotype associations and emotion recognition. Personality and Social Psychology Bulletin, 40, 5 (2014), 567\u2013577.","journal-title":"Personality and Social Psychology Bulletin"},{"key":"e_1_2_1_10_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, and Amanda Askell. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33 (2020), 1877\u20131901."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549093"},{"key":"e_1_2_1_12_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3583561","article-title":"A comprehensive empirical study of bias mitigation methods for machine learning classifiers","volume":"32","author":"Chen Zhenpeng","year":"2023","unstructured":"Zhenpeng Chen, Jie M Zhang, Federica Sarro, and Mark Harman. 2023. A comprehensive empirical study of bias mitigation methods for machine learning classifiers. ACM TOSEM, 32, 4 (2023), 1\u201330.","journal-title":"ACM TOSEM"},{"key":"e_1_2_1_13_1","volume-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, and Joseph E Gonzalez. 2023. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, March 2023. URL https:\/\/lmsys. org\/blog\/2023-03-30-vicuna, 3, 5 (2023)."},{"key":"e_1_2_1_14_1","unstructured":"Kate Crawford. 2017. The trouble with bias. keynote at neurips."},{"key":"e_1_2_1_15_1","volume-title":"Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis. 1541\u20131553","author":"Dasu Vishnu Asutosh","year":"2024","unstructured":"Vishnu Asutosh Dasu, Ashish Kumar, Saeid Tizpaz-Niari, and Gang Tan. 2024. NeuFair: Neural Network Fairness Repair with Dropout. In Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis. 1541\u20131553."},{"key":"e_1_2_1_16_1","volume-title":"Toon Calders, and Bettina Berendt.","author":"Delobelle Pieter","year":"2022","unstructured":"Pieter Delobelle, Ewoenam Kwaku Tokpo, Toon Calders, and Bettina Berendt. 2022. Measuring fairness with biased rulers: A comparative study on bias metrics for pre-trained language models. In NAACL. 1693\u20131706."},{"key":"e_1_2_1_17_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805.","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445924"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599572"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.739"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510137"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106277"},{"key":"e_1_2_1_23_1","volume-title":"Sungchul Kim","author":"Gallegos Isabel O","year":"2024","unstructured":"Isabel O Gallegos, Ryan A Rossi, Joe Barrow, Md Mehrab Tanjim, Sungchul Kim, Franck Dernoncourt, Tong Yu, Ruiyi Zhang, and Nesreen K Ahmed. 2024. Bias and fairness in large language models: A survey. Computational Linguistics, 1\u201379."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510087"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"e_1_2_1_27_1","volume-title":"Radames Cruz Moreno, and Hamed Khanpour","author":"Ghanbarzadeh Somayeh","year":"2023","unstructured":"Somayeh Ghanbarzadeh, Yan Huang, Hamid Palangi, Radames Cruz Moreno, and Hamed Khanpour. 2023. Gender-tuning: Empowering fine-tuning for debiasing pre-trained language models. arXiv:2307.10522."},{"key":"e_1_2_1_28_1","unstructured":"Ian J Goodfellow Jonathon Shlens and Christian Szegedy. 2014. Explaining and harnessing adversarial examples. ArXiv."},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462536"},{"key":"e_1_2_1_30_1","volume-title":"Equality of opportunity in supervised learning. Advances in neural information processing systems, 29","author":"Hardt Moritz","year":"2016","unstructured":"Moritz Hardt, Eric Price, and Nati Srebro. 2016. Equality of opportunity in supervised learning. Advances in neural information processing systems, 29 (2016)."},{"key":"e_1_2_1_31_1","volume-title":"Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations.","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations."},{"key":"e_1_2_1_32_1","unstructured":"Rem Hida Masahiro Kaneko and Naoaki Okazaki. 2024. Social bias evaluation for large language models requires prompt variations. arXiv:2407.03129."},{"key":"e_1_2_1_33_1","first-page":"1","article-title":"Implicit stereotypes and the predictive brain: cognition and culture in \u201cbiased\u201d person perception","volume":"3","author":"Hinton Perry","year":"2017","unstructured":"Perry Hinton. 2017. Implicit stereotypes and the predictive brain: cognition and culture in \u201cbiased\u201d person perception. Palgrave Communications, 3, 1 (2017), 1\u20139.","journal-title":"Palgrave Communications"},{"key":"e_1_2_1_34_1","volume-title":"Dan Jurafsky, and Sharese King.","author":"Hofmann Valentin","year":"2024","unstructured":"Valentin Hofmann, Pratyusha Ria Kalluri, Dan Jurafsky, and Sharese King. 2024. AI generates covertly racist decisions about people based on their dialect. Nature, 1\u20138."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3631326"},{"key":"e_1_2_1_36_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv:2106.09685.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv:2106.09685."},{"key":"e_1_2_1_37_1","first-page":"1407","article-title":"Shield against gradient leakage attacks: Adaptive privacy-preserving federated learning","volume":"32","author":"Hu Jiahui","year":"2023","unstructured":"Jiahui Hu, Zhibo Wang, Yongsheng Shen, Bohan Lin, Peng Sun, Xiaoyi Pang, Jian Liu, and Kui Ren. 2023. Shield against gradient leakage attacks: Adaptive privacy-preserving federated learning. IEEE\/ACM Transactions on Networking, 32, 2 (2023), 1407\u20131422.","journal-title":"IEEE\/ACM Transactions on Networking"},{"key":"e_1_2_1_38_1","volume-title":"Proceedings of the Eighth Annual International Conference on Shi\u2019i Studies. 166","author":"Inloes Amina","year":"2024","unstructured":"Amina Inloes. 2024. Artificial Intelligence and Islamic Theology: An Interview with ChatGPT. In Proceedings of the Eighth Annual International Conference on Shi\u2019i Studies. 166."},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1972.5008975"},{"key":"e_1_2_1_40_1","volume-title":"On information and sufficiency. The annals of mathematical statistics, 22, 1","author":"Kullback Solomon","year":"1951","unstructured":"Solomon Kullback and Richard A Leibler. 1951. On information and sufficiency. The annals of mathematical statistics, 22, 1 (1951), 79\u201386."},{"key":"e_1_2_1_41_1","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 375\u2013392","author":"Kumar Abhishek","year":"2024","unstructured":"Abhishek Kumar, Sarfaroz Yunusov, and Ali Emami. 2024. Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 375\u2013392."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.5555\/3031843.3031909"},{"key":"e_1_2_1_43_1","volume-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv:1910.13461.","author":"Lewis Mike","year":"2019","unstructured":"Mike Lewis. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv:1910.13461."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623334"},{"key":"e_1_2_1_45_1","first-page":"1","article-title":"Faire: Repairing fairness of neural networks via neuron condition synthesis","volume":"33","author":"Li Tianlin","year":"2023","unstructured":"Tianlin Li, Xiaofei Xie, Jian Wang, Qing Guo, Aishan Liu, Lei Ma, and Yang Liu. 2023. Faire: Repairing fairness of neural networks via neuron condition synthesis. ACM TOSEM, 33, 1 (2023), 1\u201324.","journal-title":"ACM TOSEM"},{"key":"e_1_2_1_46_1","unstructured":"Xinyue Li Zhenpeng Chen Jie M Zhang Yiling Lou Tianlin Li Weisong Sun Yang Liu and Xuanzhe Liu. 2024. Benchmarking Bias in Large Language Models during Role-Playing. arXiv:2411.00585."},{"key":"e_1_2_1_47_1","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu and Ananya Kumar. 2022. Holistic evaluation of language models. arXiv:2211.09110."},{"key":"e_1_2_1_48_1","volume-title":"Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, and Louis-Philippe Morency.","author":"Liang Paul Pu","year":"2020","unstructured":"Paul Pu Liang, Irene Mengze Li, Emily Zheng, Yao Chong Lim, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2020. Towards debiasing sentence representations. arXiv:2007.08100."},{"key":"e_1_2_1_49_1","unstructured":"Siyuan Liang Jiawei Liang Tianyu Pang Chao Du Aishan Liu Ee-Chien Chang and Xiaochun Cao. 2024. Revisiting Backdoor Attacks against Large Vision-Language Models. arXiv preprint arXiv:2406.18844."},{"key":"e_1_2_1_50_1","volume-title":"Badclip: Dual-embedding guided backdoor attack on multimodal contrastive learning. arXiv preprint arXiv:2311.12075.","author":"Liang Siyuan","year":"2023","unstructured":"Siyuan Liang, Mingli Zhu, Aishan Liu, Baoyuan Wu, Xiaochun Cao, and Ee-Chien Chang. 2023. Badclip: Dual-embedding guided backdoor attack on multimodal contrastive learning. arXiv preprint arXiv:2311.12075."},{"key":"e_1_2_1_51_1","unstructured":"Tomasz Limisiewicz David Mare\u010dek and Tom\u00e1\u0161 Musil. 2023. Debiasing algorithm through model adaptation. arXiv:2310.18913."},{"key":"e_1_2_1_52_1","unstructured":"Aishan Liu Xianglong Liu Jiaxin Fan Yuqing Ma Anlan Zhang Huiyuan Xie and Dacheng Tao. 2019. Perceptual-sensitive gan for generating adversarial patches. In AAAI."},{"key":"e_1_2_1_53_1","unstructured":"Aishan Liu Shiyu Tang Xinyun Chen Lei Huang Haotong Qin Xianglong Liu and Dacheng Tao. 2023. Towards Defending Multiple Lp-norm Bounded Adversarial Perturbations via Gated Batch Normalization. IJCV."},{"key":"e_1_2_1_54_1","unstructured":"Aishan Liu Jiakai Wang Xianglong Liu Bowen Cao Chongzhi Zhang and Hang Yu. 2020. Bias-based universal adversarial patch attack for automatic check-out. In ECCV."},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10287-022-00425-z"},{"key":"e_1_2_1_56_1","volume-title":"Gender bias in neural natural language processing. Logic, language, and security: essays dedicated to Andre Scedrov on the occasion of his 65th birthday, 189\u2013202","author":"Lu Kaiji","unstructured":"Kaiji Lu, Piotr Mardziel, Fangjing Wu, Preetam Amancharla, and Anupam Datta. 2020. Gender bias in neural natural language processing. Logic, language, and security: essays dedicated to Andre Scedrov on the occasion of his 65th birthday, 189\u2013202."},{"key":"e_1_2_1_57_1","unstructured":"Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras and Adrian Vladu. 2017. Towards deep learning models resistant to adversarial attacks. ArXiv."},{"key":"e_1_2_1_58_1","unstructured":"Chandler May Alex Wang Shikha Bordia Samuel R Bowman and Rachel Rudinger. 2019. On measuring social biases in sentence encoders. arXiv:1903.10561."},{"key":"e_1_2_1_59_1","doi-asserted-by":"crossref","unstructured":"Nicholas Meade Elinor Poole-Dayan and Siva Reddy. 2021. An empirical survey of the effectiveness of debiasing techniques for pre-trained language models. arXiv:2110.08527.","DOI":"10.18653\/v1\/2022.acl-long.132"},{"key":"e_1_2_1_60_1","first-page":"17359","article-title":"Locating and editing factual associations in GPT","volume":"35","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in GPT. Advances in Neural Information Processing Systems, 35 (2022), 17359\u201317372.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_61_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Meng Kevin","unstructured":"Kevin Meng, Arnab Sen Sharma, Alex J Andonian, Yonatan Belinkov, and David Bau. [n. d.]. Mass-Editing Memory in a Transformer. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_2_1_62_1","volume-title":"Proceedings of the 2024 IEEE\/ACM 46th International Conference on Software Engineering: Companion Proceedings. 402\u2013403","author":"Monjezi Verya","year":"2024","unstructured":"Verya Monjezi, Ashish Kumar, Gang Tan, Ashutosh Trivedi, and Saeid Tizpaz-Niari. 2024. Causal Graph Fuzzing for Fair ML Sofware Development. In Proceedings of the 2024 IEEE\/ACM 46th International Conference on Software Engineering: Companion Proceedings. 402\u2013403."},{"key":"e_1_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Verya Monjezi Ashutosh Trivedi Vladik Kreinovich and Saeid Tizpaz-Niari. 2025. Fairness Testing through Extreme Value Theory. arXiv:2501.11597.","DOI":"10.1109\/ICSE55347.2025.00070"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00136"},{"key":"e_1_2_1_65_1","doi-asserted-by":"crossref","unstructured":"Moin Nadeem Anna Bethke and Siva Reddy. 2020. StereoSet: Measuring stereotypical bias in pretrained language models. arXiv:2004.09456.","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"e_1_2_1_66_1","doi-asserted-by":"crossref","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:2010.00133.","DOI":"10.18653\/v1\/2020.emnlp-main.154"},{"key":"e_1_2_1_67_1","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 16366\u201316393","author":"Naous Tarek","year":"2024","unstructured":"Tarek Naous, Michael J Ryan, Alan Ritter, and Wei Xu. 2024. Having Beer after Prayer? Measuring Cultural Bias in Large Language Models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 16366\u201316393."},{"key":"e_1_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2013-001964"},{"key":"e_1_2_1_69_1","volume-title":"Phu Mon Htut, and Samuel R Bowman","author":"Parrish Alicia","year":"2021","unstructured":"Alicia Parrish, Angelica Chen, Nikita Nangia, Vishakh Padmakumar, Jason Phang, Jana Thompson, Phu Mon Htut, and Samuel R Bowman. 2021. BBQ: A hand-built bias benchmark for question answering. arXiv:2110.08193."},{"key":"e_1_2_1_70_1","unstructured":"Alec Radford. 2018. Improving language understanding by generative pre-training."},{"key":"e_1_2_1_71_1","volume-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society. 7, 1180\u20131189","author":"Raj Chahat","year":"2024","unstructured":"Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, and Ziwei Zhu. 2024. Breaking bias, building bridges: Evaluation and mitigation of social biases in llms via contact hypothesis. In Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society. 7, 1180\u20131189."},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00918"},{"key":"e_1_2_1_73_1","doi-asserted-by":"crossref","unstructured":"Shauli Ravfogel Yanai Elazar Hila Gonen Michael Twiton and Yoav Goldberg. 2020. Null it out: Guarding protected attributes by iterative nullspace projection. arXiv:2004.07667.","DOI":"10.18653\/v1\/2020.acl-main.647"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00434"},{"key":"e_1_2_1_75_1","unstructured":"Chenglei Si Zhe Gan Zhengyuan Yang Shuohang Wang Jianfeng Wang Jordan Boyd-Graber and Lijuan Wang. 2022. Prompting gpt-3 to be reliable. arXiv:2210.09150."},{"key":"e_1_2_1_76_1","first-page":"5188","article-title":"Astraea: Grammar-based fairness testing","volume":"48","author":"Soremekun Ezekiel","year":"2022","unstructured":"Ezekiel Soremekun, Sakshi Udeshi, and Sudipta Chattopadhyay. 2022. Astraea: Grammar-based fairness testing. IEEE Transactions on Software Engineering, 48, 12 (2022), 5188\u20135211.","journal-title":"IEEE Transactions on Software Engineering"},{"key":"e_1_2_1_77_1","volume-title":"End-to-end memory networks. Advances in neural information processing systems, 28","author":"Sukhbaatar Sainbayar","year":"2015","unstructured":"Sainbayar Sukhbaatar, Jason Weston, and Rob Fergus. 2015. End-to-end memory networks. Advances in neural information processing systems, 28 (2015)."},{"key":"e_1_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510080"},{"key":"e_1_2_1_79_1","doi-asserted-by":"crossref","unstructured":"Zeyu Sun Zhenpeng Chen Jie Zhang and Dan Hao. 2024. Fairness Testing of Machine Translation Systems. ACM TOSEM.","DOI":"10.1145\/3664608"},{"key":"e_1_2_1_80_1","unstructured":"Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna Dumitru Erhan Ian Goodfellow and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv:1312.6199."},{"key":"e_1_2_1_81_1","volume-title":"Robustart: Benchmarking robustness on architecture design and training techniques. ArXiv.","author":"Tang Shiyu","year":"2021","unstructured":"Shiyu Tang, Ruihao Gong, Yan Wang, Aishan Liu, Jiakai Wang, Xinyun Chen, Fengwei Yu, Xianglong Liu, Dawn Song, and Alan Yuille. 2021. Robustart: Benchmarking robustness on architecture design and training techniques. ArXiv."},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3540250.3549169"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510202"},{"key":"e_1_2_1_84_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava and Shruti Bhosale. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288."},{"key":"e_1_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616310"},{"key":"e_1_2_1_86_1","doi-asserted-by":"crossref","unstructured":"Jiakai Wang Aishan Liu Zixin Yin Shunchang Liu Shiyu Tang and Xianglong Liu. 2021. Dual attention suppression attack: Generate adversarial camouflage in physical world. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00846"},{"key":"e_1_2_1_87_1","doi-asserted-by":"crossref","unstructured":"Wenxuan Wang Haonan Bai Jen-tse Huang Yuxuan Wan Youliang Yuan Haoyi Qiu Nanyun Peng and Michael R Lyu. 2024. New Job New Gender? Measuring the Social Bias in Image Generation Models. arXiv:2401.00763.","DOI":"10.1145\/3664647.3681433"},{"key":"e_1_2_1_88_1","doi-asserted-by":"crossref","first-page":"2269","DOI":"10.1109\/TMC.2023.3254553","article-title":"Location privacy-aware task offloading in mobile edge computing","volume":"23","author":"Wang Zhibo","year":"2023","unstructured":"Zhibo Wang, Yunan Sun, Defang Liu, Jiahui Hu, Xiaoyi Pang, Yuke Hu, and Kui Ren. 2023. Location privacy-aware task offloading in mobile edge computing. IEEE Transactions on Mobile Computing, 23, 3 (2023), 2269\u20132283.","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_2_1_89_1","volume-title":"Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. 1\u201312","author":"Wang Zhaohui","year":"2024","unstructured":"Zhaohui Wang, Min Zhang, Jingran Yang, Bojie Shao, and Min Zhang. 2024. MAFT: Efficient Model-Agnostic Fairness Testing for Deep Neural Networks via Zero-Order Gradient Search. In Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering. 1\u201312."},{"key":"e_1_2_1_90_1","volume-title":"Chi, and Slav Petrov","author":"Webster Kellie","year":"2020","unstructured":"Kellie Webster, Xuezhi Wang, Ian Tenney, Alex Beutel, Emily Pitler, Ellie Pavlick, Jilin Chen, Ed Chi, and Slav Petrov. 2020. Measuring and reducing gendered correlations in pre-trained models. arXiv:2010.06032."},{"key":"e_1_2_1_91_1","unstructured":"Yisong Xiao Aishan Liu QianJia Cheng Zhenfei Yin Siyuan Liang Jiapeng Li Jing Shao Xianglong Liu and Dacheng Tao. 2024. GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing. arXiv preprint arXiv:2407.00600."},{"key":"e_1_2_1_92_1","doi-asserted-by":"crossref","unstructured":"Yisong Xiao Aishan Liu Tianlin Li and Xianglong Liu. 2023. Latent imitator: Generating natural individual discriminatory instances for black-box fairness testing. In ISSTA. 829\u2013841.","DOI":"10.1145\/3597926.3598099"},{"key":"e_1_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-023-00031-w"},{"key":"e_1_2_1_94_1","doi-asserted-by":"crossref","DOI":"10.1109\/TSC.2024.3451185","article-title":"When search engine services meet large language models: visions and challenges","author":"Xiong Haoyi","year":"2024","unstructured":"Haoyi Xiong, Jiang Bian, Yuchen Li, Xuhong Li, Mengnan Du, Shuaiqiang Wang, Dawei Yin, and Sumi Helal. 2024. When search engine services meet large language models: visions and challenges. IEEE Transactions on Services Computing.","journal-title":"IEEE Transactions on Services Computing."},{"key":"e_1_2_1_95_1","volume-title":"Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING","author":"Yeh Kai-Ching","year":"2023","unstructured":"Kai-Ching Yeh, Jou-An Chi, Da-Chen Lian, and Shu-Kai Hsieh. 2023. Evaluating interfaced llm bias. In Proceedings of the 35th Conference on Computational Linguistics and Speech Processing (ROCLING 2023). 292\u2013299."},{"key":"e_1_2_1_96_1","doi-asserted-by":"crossref","unstructured":"Mengdi Zhang and Jun Sun. 2022. Adaptive fairness improvement based on causality analysis. In ESEC\/FSE. 6\u201317.","DOI":"10.1145\/3540250.3549103"},{"key":"e_1_2_1_97_1","volume-title":"Jin Song Dong, and Ting Dai","author":"Zhang Peixin","year":"2020","unstructured":"Peixin Zhang, Jingyi Wang, Jun Sun, Guoliang Dong, Xinyu Wang, Xingen Wang, Jin Song Dong, and Ting Dai. 2020. White-box fairness testing through adversarial sampling. In ICSE. 949\u2013960."},{"key":"e_1_2_1_98_1","doi-asserted-by":"crossref","unstructured":"Jieyu Zhao Tianlu Wang Mark Yatskar Vicente Ordonez and Kai-Wei Chang. 2018. Gender bias in coreference resolution: Evaluation and debiasing methods. arXiv:1804.06876.","DOI":"10.18653\/v1\/N18-2003"},{"key":"e_1_2_1_99_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510123"},{"key":"e_1_2_1_100_1","volume-title":"Llamafactory: Unified efficient fine-tuning of 100+ language models. arXiv:2403.13372.","author":"Zheng Yaowei","year":"2024","unstructured":"Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, and Zheyan Luo. 2024. Llamafactory: Unified efficient fine-tuning of 100+ language models. arXiv:2403.13372."}],"container-title":["Proceedings of the ACM on Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3728881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T16:52:58Z","timestamp":1752684778000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3728881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":100,"journal-issue":{"issue":"ISSTA","published-print":{"date-parts":[[2025,6,22]]}},"alternative-id":["10.1145\/3728881"],"URL":"https:\/\/doi.org\/10.1145\/3728881","relation":{},"ISSN":["2994-970X"],"issn-type":[{"value":"2994-970X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,22]]}}}