{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T07:01:25Z","timestamp":1771743685211,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":46,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570805","type":"print"},{"value":"9789819570812","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-7081-2_3","type":"book-chapter","created":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T06:46:42Z","timestamp":1771742802000},"page":"35-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PRISM: Principled Reasoning for\u00a0Identifying and\u00a0Suppressing Model Biases at\u00a0Scale"],"prefix":"10.1007","author":[{"given":"Xunfei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weitong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkai","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Abid, A., Farooqi, M., Zou, J.: Persistent anti-muslim bias in large language models. In: Proceedings of the 2021 AAAI\/ACM Conference on AI, Ethics, and Society. pp. 298\u2013306 (2021)","DOI":"10.1145\/3461702.3462624"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Atwany, H., Waheed, A., Singh, R., Choudhury, M., Raj, B.: Lost in transcription, found in distribution shift: Demystifying hallucination in speech foundation models (2025). https:\/\/arxiv.org\/abs\/2502.12414","DOI":"10.18653\/v1\/2025.findings-acl.1190"},{"key":"3_CR3","first-page":"373","volume":"31","author":"RS Baker","year":"2021","unstructured":"Baker, R.S., Hawn, A.: Algorithmic bias in education. Int. J. Artif. Intell. Educ. 31, 373\u2013388 (2021)","journal-title":"Int. J. Artif. Intell. Educ."},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Blodgett, S.L., Barocas, S., Daum\u00e9\u00a0III, H., Wallach, H.: Language (technology) is power: a critical survey of \u201cbias\" in nlp. arXiv preprint arXiv:2005.14050 (2020)","DOI":"10.18653\/v1\/2020.acl-main.485"},{"key":"3_CR5","unstructured":"Bolukbasi, T., Chang, K.W., Zou, J.Y., Saligrama, V., Kalai, A.T.: Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Adv. Neu. Inf. Process. Sys. 29 (2016)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Campesato, O.: CSS3 and SVG with Claude 3. Walter de Gruyter GmbH & Co KG (2024)","DOI":"10.1515\/9781501520693"},{"key":"3_CR7","unstructured":"Chang, Y., Chang, Y., Wu, Y.: Ba-lora: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models (2025). https:\/\/arxiv.org\/abs\/2408.04556"},{"key":"3_CR8","unstructured":"Chen, Z., Liu, T., Tian, M., Tong, Q., Luo, W., Liu, Z.: Advancing math reasoning in language models: The impact of problem-solving data, data synthesis methods, and training stages. arXiv preprint arXiv:2501.14002 (2025)"},{"key":"3_CR9","unstructured":"Dev, S., Li, T., Phillips, J.M., Srikumar, V.: Measuring and reducing gendered correlations in pre-trained models. In: arXiv preprint arXiv:2010.06032 (2020)"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Dinan, E., Fan, A., Williams, A., Urbanek, J., Kiela, D., Weston, J.: Queens are powerful too: Mitigating gender bias in dialogue generation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). pp. 8173\u20138188 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.656"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Evans, A.S., Moniz, H., Coheur, L.: A study on bias detection and classification in natural language processing (2024). https:\/\/arxiv.org\/abs\/2408.07479","DOI":"10.21203\/rs.3.rs-3351695\/v1"},{"key":"3_CR12","unstructured":"Fayyaz, H., Poulain, R., Beheshti, R.: Enabling scalable evaluation of bias patterns in medical LLMs (2025). https:\/\/openreview.net\/forum?id=IXGHSVBBCF"},{"issue":"3","key":"3_CR13","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1162\/coli_a_00524","volume":"50","author":"IO Gallegos","year":"2024","unstructured":"Gallegos, I.O., et al.: Bias and fairness in large language models: a survey. Comput. Linguist. 50(3), 1097\u20131179 (2024)","journal-title":"Comput. Linguist."},{"key":"3_CR14","unstructured":"Ganguli, D., et\u00a0al.: Red teaming language models with language models. arXiv preprint arXiv:2202.03286 (2022)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Gururangan, S., Swayamdipta, S., Levy, O., Schwartz, R., Bowman, S.R., Smith, N.A.: Annotation artifacts in natural language inference data. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics. pp. 107\u2013112 (2018)","DOI":"10.18653\/v1\/N18-2017"},{"issue":"3","key":"3_CR16","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1162\/qss_a_00310","volume":"5","author":"A Hajikhani","year":"2024","unstructured":"Hajikhani, A., Cole, C.: A critical review of large language models: Sensitivity, bias, and the path toward specialized ai. Quant. Sci. Stud. 5(3), 736\u2013756 (2024)","journal-title":"Quant. Sci. Stud."},{"key":"3_CR17","unstructured":"Hurst, A., et\u00a0al.: Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, M., et al.: Item-side fairness of large language model-based recommendation system. In: Proceedings of the ACM Web Conference 2024. pp. 4717\u20134726 (2024)","DOI":"10.1145\/3589334.3648158"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Kabir, M.R., et al.: Beyond labels: Aligning large language models with human-like reasoning. In: Antonacopoulos, A., Chaudhuri, S., Chellappa, R., Liu, CL., Bhattacharya, S., Pal, U. (eds.) International Conference on Pattern Recognition. pp. 239\u2013254. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-78172-8_16","DOI":"10.1007\/978-3-031-78172-8_16"},{"key":"3_CR20","unstructured":"Ko, Y., et al.: Length bias in language models: Quantifying, explaining, and mitigating across model scales. In: arXiv preprint arXiv:2310.00136 (2023)"},{"key":"3_CR21","doi-asserted-by":"publisher","unstructured":"Kumar, A., et al.: Debiasing counterfactuals in the presence of spurious correlations. In: Workshop on Clinical Image-Based Procedures. pp. 276\u2013286. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-45249-9_27","DOI":"10.1007\/978-3-031-45249-9_27"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Levy, S., Adler, W., Karver, T., Dredze, M., Kaufman, M.: Gender bias in decision-making with large language models: A study of relationship conflicts. In: Findings of the Association for Computational Linguistics: EMNLP 2024. pp. 5777\u20135800 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.331"},{"key":"3_CR23","unstructured":"Li, A., et al.: Mitigating biases of large language models in stance detection with counterfactual augmented calibration. arXiv preprint arXiv:2402.14296 (2024)"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Li, L., et\u00a0al.: Debiasing in-context learning by instructing llms how to follow demonstrations. In: Findings of the Association for Computational Linguistics ACL 2024. pp. 7203\u20137215 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.430"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Li, T., Khashabi, D., Khot, T., Sabharwal, A., Srikumar, V.: Unqovering stereotyping biases via underspecified questions. In: Findings of the Association for Computational Linguistics: EMNLP 2020. pp. 3475\u20133489 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.311"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Lu, Y., Bartolo, M., Moore, A., Riedel, S., Stenetorp, P.: Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. pp. 8086\u20138098 (2022)","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Matzken, C., Eger, S., Habernal, I.: Trade-offs between fairness and privacy in language modeling. In: Findings of the Association for Computational Linguistics: ACL 2023. pp. 6948\u20136969 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.434"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"McCoy, R.T., Pavlick, E., Linzen, T.: Right for the wrong reasons: Diagnosing syntactic heuristics in natural language inference. arXiv preprint arXiv:1902.01007 (2019)","DOI":"10.18653\/v1\/P19-1334"},{"key":"3_CR29","unstructured":"Narayan, M., Pasmore, J., Sampaio, E., Raghavan, V., Waters, G.: Bias neutralization framework: Measuring fairness in large language models with bias intelligence quotient (biq) (2024). https:\/\/arxiv.org\/abs\/2404.18276"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Parrish, A., et al.: Bbq: A hand-built bias benchmark for question answering. In: Findings of the Association for Computational Linguistics: ACL 2022. pp. 2086\u20132105 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Ravfogel, S., Twiton, M., Goldberg, Y., Cotterell, R.D.: Linear adversarial concept erasure. In: International Conference on Machine Learning. pp. 18400\u201318421. PMLR (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.405"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Sap, M., Card, D., Gabriel, S., Choi, Y., Smith, N.A.: The risk of racial bias in hate speech detection. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. pp. 1668\u20131678 (2019)","DOI":"10.18653\/v1\/P19-1163"},{"key":"3_CR33","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1162\/tacl_a_00434","volume":"9","author":"T Schick","year":"2021","unstructured":"Schick, T., Udupa, S., Sch\u00fctze, H.: Self-diagnosis and self-debiasing: A proposal for reducing corpus-based bias in nlp. Trans. Assoc. Comput. Linguis. 9, 1408\u20131424 (2021)","journal-title":"Trans. Assoc. Comput. Linguis."},{"key":"3_CR34","unstructured":"Si, R., Ganhotra, J., Khan, M.M.R., Tesauro, G., Soricut, R.: Prompting for multimodal hateful meme classification. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. pp. 7255\u20137268 (2022)"},{"key":"3_CR35","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Causal-guided active learning for debiasing large language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 14455\u201314469 (2024)","DOI":"10.18653\/v1\/2024.acl-long.778"},{"key":"3_CR36","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"3_CR37","unstructured":"Wang, H., Wu, L., Zhou, Y., Mo, Y., Lin, H., Yu, H.: Position bias mitigation: A knowledge-aware graph model for emotion cause extraction. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics. pp. 4946\u20134957 (2022)"},{"key":"3_CR38","unstructured":"Wang, Z., Wu, Z., Zhang, J., Jain, N., Guan, X., Koshiyama, A.: Bias amplification: Language models as increasingly biased media. arXiv preprint arXiv:2410.15234 (2024)"},{"key":"3_CR39","unstructured":"Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems. vol.\u00a035, pp. 24824\u201324837 (2022)"},{"key":"3_CR40","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., Bowman, S.R.: A broad-coverage challenge corpus for sentence understanding through inference. In: 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018. pp. 1112\u20131122. Association for Computational Linguistics (ACL) (2018)","DOI":"10.18653\/v1\/N18-1101"},{"key":"3_CR41","unstructured":"Zhang, J., Yang, L., Liu, Q., Zhang, Y.: Health misinformation detection in large language models: An empirical study of chatgpt on misleading health claims. arXiv preprint arXiv:2310.05490 (2023)"},{"key":"3_CR42","unstructured":"Zhao, J., Fang, M., Pan, S., Yin, W., Pechenizkiy, M.: GPTBIAS: A comprehensive framework for evaluating bias in large language models (2024). https:\/\/openreview.net\/forum?id=u1EPPYkbgA"},{"key":"3_CR43","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, F., Mao, Y., Yu, L., Yang, Y., Zhong, T.: Causal-debias: Unifying debiasing in pretrained language models and fine-tuning via causal invariant learning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 4227\u20134241 (2023)","DOI":"10.18653\/v1\/2023.acl-long.232"},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, K., Zhang, B., Zhao, W.X., Wen, J.R.: Debiased contrastive learning of unsupervised sentence representations. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp. 6120\u20136130 (2022)","DOI":"10.18653\/v1\/2022.acl-long.423"},{"key":"3_CR46","unstructured":"Zhou, N., Zhang, Z., Nair, V.N., Singhal, H., Chen, J., Sudjianto, A.: Bias, fairness, and accountability with ai and ml algorithms (2021). https:\/\/arxiv.org\/abs\/2105.06558"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7081-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T06:46:53Z","timestamp":1771742813000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7081-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570805","9789819570812"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7081-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}