{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:27:48Z","timestamp":1771064868248,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3770355","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"951-959","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Unmasking Bias in Financial AI: A Robust Framework for Evaluating and Mitigating Hidden Biases in LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6980-2392","authenticated-orcid":false,"given":"Shreshth","family":"Mehrotra","sequence":"first","affiliation":[{"name":"Mastercard, Gurugram, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1767-8276","authenticated-orcid":false,"given":"Raghavendra","family":"P","sequence":"additional","affiliation":[{"name":"Mastercard, Gurugram, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9014-2871","authenticated-orcid":false,"given":"Balraj","family":"Prajesh","sequence":"additional","affiliation":[{"name":"Mastercard, Gurugram, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8600-5794","authenticated-orcid":false,"given":"Hrishikesh","family":"Kambale","sequence":"additional","affiliation":[{"name":"Mastercard, Gurugram, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4031-785X","authenticated-orcid":false,"given":"Puspita","family":"Majumdar","sequence":"additional","affiliation":[{"name":"Mastercard, Gurugram, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal et\u00a0al. 2023. GPT-4 Technical Report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_3_2","unstructured":"Joshua Barron and Devin White. 2025. Too Big to Think: Capacity Memorization and Generalization in Pre-Trained Transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09099 (2025)."},{"key":"e_1_3_3_2_4_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder 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_5_2","doi-asserted-by":"crossref","unstructured":"Aylin Caliskan Joanna\u00a0J Bryson and Arvind Narayanan. 2017. Semantics Derived Automatically from Language Corpora contain Human-like Biases. Science 356 6334 (2017) 183\u2013186.","DOI":"10.1126\/science.aal4230"},{"key":"e_1_3_3_2_6_2","first-page":"52","volume-title":"International Conference on Discovery Science","author":"Cantini Riccardo","year":"2024","unstructured":"Riccardo Cantini, Giada Cosenza, Alessio Orsino, et\u00a0al. 2024. Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation. In International Conference on Discovery Science. Springer, 52\u201368."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML64287.2025.00010"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445924"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Emilio Ferrara. 2023. Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models. https:\/\/api.semanticscholar.org\/CorpusID:258041203","DOI":"10.2139\/ssrn.4627814"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Isabel\u00a0O Gallegos Ryan\u00a0A Rossi Joe Barrow et\u00a0al. 2024. Bias and fairness in large language models: A survey. Computational Linguistics 50 3 (2024) 1097\u20131179.","DOI":"10.1162\/coli_a_00524"},{"key":"e_1_3_3_2_11_2","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_2_12_2","unstructured":"Vipul Gupta Pranav\u00a0Narayanan Venkit Hugo Lauren\u00e7on et\u00a0al. 2023. CALM: A Multi-task Benchmark for Comprehensive Assessment of Language Model Bias. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.12539 (2023)."},{"key":"e_1_3_3_2_13_2","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_3_3_2_14_2","unstructured":"Pengcheng He Jianfeng Gao and Weizhu Chen. 2021. Debertav3: Improving Deberta using Electra-style Pre-training with Gradient-Disentangled Embedding Sharing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.09543 (2021)."},{"key":"e_1_3_3_2_15_2","unstructured":"Albert\u00a0Q Jiang Alexandre Sablayrolles Antoine Roux et\u00a0al. 2024. Mixtral of Experts. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.04088 (2024)."},{"key":"e_1_3_3_2_16_2","unstructured":"Haibo Jin Ruoxi Chen Peiyan Zhang et\u00a0al. 2024. GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models. ICLR Workshop on Secure and Trustworthy Large Language Models (2024)."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","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. 62nd Annual Meeting of the Association for Computational Linguistics (2024) 375\u2013392.","DOI":"10.18653\/v1\/2024.acl-long.23"},{"key":"e_1_3_3_2_18_2","unstructured":"Kristian Lum Jacy\u00a0Reese Anthis Kevin Robinson et\u00a0al. 2024. Bias in language models: Beyond trick tests and toward ruted evaluation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.12649 (2024)."},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Marta\u00a0Marchiori Manerba Karolina Sta\u0144czak Riccardo Guidotti et\u00a0al. 2024. Social Bias Probing: Fairness Benchmarking for Language Models. Conference on Empirical Methods in Natural Language Processing (2024).","DOI":"10.18653\/v1\/2024.emnlp-main.812"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Chandler May Alex Wang Shikha Bordia et\u00a0al. 2019. On Measuring Social Biases in Sentence Encoders. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. (2019) 622\u2013628.","DOI":"10.18653\/v1\/N19-1063"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Anay Mehrotra Manolis Zampetakis Paul Kassianik et\u00a0al. 2024. Tree of Attacks: Jailbreaking Black-Box LLMs Automatically. Advances in Neural Information Processing Systems 37 (2024) 61065\u201361105.","DOI":"10.52202\/079017-1952"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Moin Nadeem Anna Bethke and Siva Reddy. 2021. StereoSet: Measuring stereotypical bias in pretrained language models. 59th Annual Meeting of the Association for Computational Linguistics and 11th International Joint Conference on Natural Language Processing (2021) 5356\u20135371.","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"e_1_3_3_2_23_2","unstructured":"Abiodun\u00a0Finbarrs Oketunji Muhammad Anas and Deepthi Saina. 2023. Large Language Model (LLM) Bias Index\u2013LLMBI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.14769 (2023)."},{"key":"e_1_3_3_2_24_2","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang et\u00a0al. 2022. Training Language Models to Follow Instructions with Human Feedback. Advances in Neural Information Processing Systems 35 (2022) 27730\u201327744."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Alicia Parrish Angelica Chen Nikita Nangia et\u00a0al. 2022. BBQ: A Hand-Built Bias Benchmark for Question Answering. Findings of the Association for Computational Linguistics: ACL 2022 (2022) 2086\u20132105.","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"key":"e_1_3_3_2_26_2","unstructured":"Ali Satvaty Suzan Verberne and Fatih Turkmen. 2024. Undesirable memorization in large language models: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.02650 (2024)."},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Timo Schick Sahana Udupa and Hinrich Sch\u00fctze. 2021. Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP. Transactions of the Association for Computational Linguistics 9 (2021) 1408\u20131424.","DOI":"10.1162\/tacl_a_00434"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Emily Sheng Kai-Wei Chang Premkumar Natarajan et\u00a0al. 2019. The Woman Worked as a Babysitter: On Biases in Language Generation. Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (2019) 3407\u20133412.","DOI":"10.18653\/v1\/D19-1339"},{"key":"e_1_3_3_2_29_2","unstructured":"Chenglei Si Zhe Gan Zhengyuan Yang et\u00a0al. 2023. Prompting GPT-3 To Be Reliable. 11th International Conference on Learning Representations (2023)."},{"key":"e_1_3_3_2_30_2","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:https:\/\/arXiv.org\/abs\/2206.09860 (2022)."},{"key":"e_1_3_3_2_31_2","unstructured":"Gemma Team Morgane Riviere Shreya Pathak et\u00a0al. 2024. Gemma 2: Improving Open Language Models at a Practical Size. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.00118 (2024)."},{"key":"e_1_3_3_2_32_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard et\u00a0al. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_2_33_2","unstructured":"Boxin Wang Chejian Xu Shuohang Wang et\u00a0al. 2021. Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models. Neural Information Processing Systems Track on Datasets and Benchmarks (2021)."},{"key":"e_1_3_3_2_34_2","unstructured":"Laura Weidinger John Mellor Maribeth Rauh et\u00a0al. 2021. Ethical and Social Risks of Harm from Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2112.04359 (2021)."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.773"}],"event":{"name":"ICAIF '25: 6th ACM International Conference on AI in Finance","location":"Singapore Singapore","acronym":"ICAIF '25"},"container-title":["Proceedings of the 6th ACM International Conference on AI in Finance"],"original-title":[],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:30:10Z","timestamp":1763105410000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3770355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":34,"alternative-id":["10.1145\/3768292.3770355","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3770355","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}