{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:39:01Z","timestamp":1778251141614,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819756711","type":"print"},{"value":"9789819756728","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5672-8_40","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T19:02:53Z","timestamp":1722538973000},"page":"471-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Locating and Mitigating Gender Bias in Large Language Models"],"prefix":"10.1007","author":[{"given":"Yuchen","family":"Cai","sequence":"first","affiliation":[]},{"given":"Ding","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Rongxi","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yaqin","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Guiquan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Enhong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"40_CR1","doi-asserted-by":"crossref","unstructured":"Bisk, Y., Zellers, R., Gao, J., Choi, Y., et al.: PIQA: Reasoning about physical commonsense in natural language. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7432\u20137439 (2020)","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"40_CR2","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. Neural Inf. Process. Syst. 29 (2016)"},{"issue":"6334","key":"40_CR3","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1126\/science.aal4230","volume":"356","author":"A Caliskan","year":"2017","unstructured":"Caliskan, A., Bryson, J.J., Narayanan, A.: Semantics derived automatically from language corpora contain human-like biases. Science 356(6334), 183\u2013186 (2017)","journal-title":"Science"},{"key":"40_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, S., et al.: Can we edit multimodal large language models? (2023) arXiv:2310.08475","DOI":"10.18653\/v1\/2023.emnlp-main.856"},{"key":"40_CR5","unstructured":"Cheng, S., et al.: Editing language model-based knowledge graph embeddings (2023). arXiv:2301.10405"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Choi, J.H., Hickman, K.E., Monahan, A., Schwarcz, D.: ChatGPT goes to law school (2023)","DOI":"10.2139\/ssrn.4335905"},{"key":"40_CR7","unstructured":"Cohen, D., et al.: Dynamic planning in open-ended dialogue using reinforcement learning (2022). arXiv:2208.02294"},{"key":"40_CR8","unstructured":"Dai, D., Dong, L., Hao, Y., Sui, Z., Wei, F.: Knowledge neurons in pretrained transformers (2021). arXiv abs\/2104.08696. https:\/\/api.semanticscholar.org\/CorpusID:233296761"},{"key":"40_CR9","doi-asserted-by":"crossref","unstructured":"Ferrara, E.: Should chatGPT be biased? Challenges and risks of bias in large language models (2023). arXiv:2304.03738","DOI":"10.2139\/ssrn.4627814"},{"key":"40_CR10","doi-asserted-by":"crossref","unstructured":"Gandikota, R., Materzynska, J., Fiotto-Kaufman, J., Bau, D.: Erasing concepts from diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2426\u20132436 (2023)","DOI":"10.1109\/ICCV51070.2023.00230"},{"issue":"16","key":"40_CR11","doi-asserted-by":"crossref","first-page":"E3635","DOI":"10.1073\/pnas.1720347115","volume":"115","author":"N Garg","year":"2018","unstructured":"Garg, N., Schiebinger, L., Jurafsky, D., Zou, J.: Word embeddings quantify 100 years of gender and ethnic stereotypes. Proc. Natl. Acad. Sci. U.S.A. 115(16), E3635\u2013E3644 (2018)","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"40_CR12","doi-asserted-by":"crossref","unstructured":"Geva, M., Bastings, J., Filippova, K., Globerson, A.: Dissecting recall of factual associations in auto-regressive language models (2023). arXiv abs\/2304.14767. https:\/\/api.semanticscholar.org\/CorpusID:258417932","DOI":"10.18653\/v1\/2023.emnlp-main.751"},{"key":"40_CR13","doi-asserted-by":"crossref","unstructured":"Geva, M., Caciularu, A., Wang, K., Goldberg, Y.: Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space (2022). arXiv abs\/2203.14680. https:\/\/api.semanticscholar.org\/CorpusID:247762385","DOI":"10.18653\/v1\/2022.emnlp-main.3"},{"issue":"1","key":"40_CR14","volume":"9","author":"A Gilson","year":"2023","unstructured":"Gilson, A., et al.: How does chatGPT perform on the united states medical licensing examination? The implications of large language models for medical education and knowledge assessment. JMIR Med. Educ. 9(1), e45312 (2023)","journal-title":"JMIR Med. Educ."},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Guo, Y., Yang, Y., Abbasi, A.: Auto-debias: debiasing masked language models with automated biased prompts. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1012\u20131023 (2022)","DOI":"10.18653\/v1\/2022.acl-long.72"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Kohonen, T.: Correlation matrix memories. IEEE Trans. Comput. C-21, 353\u2013359 (1972). https:\/\/api.semanticscholar.org\/CorpusID:21483100","DOI":"10.1109\/TC.1972.5008975"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"May, C., Wang, A., Bordia, S., Bowman, S.R., Rudinger, R.: On measuring social biases in sentence encoders (2019). arXiv:1903.10561","DOI":"10.18653\/v1\/N19-1063"},{"key":"40_CR18","first-page":"17359","volume":"35","author":"K Meng","year":"2022","unstructured":"Meng, K., Bau, D., Andonian, A., Belinkov, Y.: Locating and editing factual associations in GPT. Adv. Neural. Inf. Process. Syst. 35, 17359\u201317372 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"40_CR19","unstructured":"Meng, K., Sharma, A.S., Andonian, A., Belinkov, Y., Bau, D.: Mass-editing memory in a transformer (2022). arXiv:2210.07229"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Paperno, D., et al.: The LAMBADA dataset: word prediction requiring a broad discourse context (2016). arXiv:1606.06031","DOI":"10.18653\/v1\/P16-1144"},{"key":"40_CR21","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019). https:\/\/api.semanticscholar.org\/CorpusID:160025533"},{"key":"40_CR22","unstructured":"Ramamurthy, R., et al.: Is reinforcement learning (not) for natural language processing? Benchmarks, baselines, and building blocks for natural language policy optimization (2022). arXiv:2210.01241"},{"key":"40_CR23","unstructured":"Roemmele, M., Bejan, C.A., Gordon, A.S.: Choice of plausible alternatives: an evaluation of commonsense causal reasoning. In: 2011 AAAI Spring Symposium Series (2011)"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Rudinger, R., Naradowsky, J., Leonard, B., Van Durme, B.: Gender bias in coreference resolution (2018). arXiv:1804.09301","DOI":"10.18653\/v1\/N18-2002"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Sap, M., Rashkin, H., Chen, D., LeBras, R., Choi, Y.: Socialiqa: commonsense reasoning about social interactions (2019). arXiv:1904.09728","DOI":"10.18653\/v1\/D19-1454"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Sun, T., et al.: Mitigating gender bias in natural language processing: literature review (2019). arXiv:1906.08976","DOI":"10.18653\/v1\/P19-1159"},{"key":"40_CR27","unstructured":"Talmor, A., Herzig, J., Lourie, N., Berant, J.: Commonsenseqa: a question answering challenge targeting commonsense knowledge (2018). arXiv:1811.00937"},{"key":"40_CR28","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023). arXiv:2302.13971"},{"key":"40_CR29","unstructured":"Vig, J., et al.: Causal mediation analysis for interpreting neural NLP: the case of gender bias (2020). arXiv:2004.12265"},{"key":"40_CR30","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: Glue: a multi-task benchmark and analysis platform for natural language understanding (2018). arXiv:1804.07461","DOI":"10.18653\/v1\/W18-5446"},{"key":"40_CR31","unstructured":"Wang, B., Komatsuzaki, A.: GPT-J-6B: a 6 billion parameter autoregressive language model (2021)"},{"key":"40_CR32","unstructured":"Webster, K., et al.: Measuring and reducing gendered correlations in pre-trained models (2020). arXiv:2010.06032"},{"key":"40_CR33","unstructured":"Yang, A., et al.: Baichuan 2: open large-scale language models (2023). arXiv:2309.10305"},{"key":"40_CR34","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: Editing large language models: problems, methods, and opportunities (2023). arXiv:2305.13172","DOI":"10.18653\/v1\/2023.emnlp-main.632"},{"key":"40_CR35","doi-asserted-by":"crossref","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: Hellaswag: can a machine really finish your sentence? (2019). arXiv:1905.07830","DOI":"10.18653\/v1\/P19-1472"},{"key":"40_CR36","doi-asserted-by":"crossref","unstructured":"Zhao, J., Wang, T., Yatskar, M., Ordonez, V., Chang, K.W.: Gender bias in coreference resolution: evaluation and debiasing methods (2018). arXiv:1804.06876","DOI":"10.18653\/v1\/N18-2003"},{"key":"40_CR37","unstructured":"Ziegler, D.M., et al.: Fine-tuning language models from human preferences (2019). arXiv:1909.08593"},{"key":"40_CR38","doi-asserted-by":"crossref","unstructured":"Zmigrod, R., Mielke, S.J., Wallach, H., Cotterell, R.: Counterfactual data augmentation for mitigating gender stereotypes in languages with rich morphology. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 1651\u20131661 (2019)","DOI":"10.18653\/v1\/P19-1161"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Cai, Y., Cao, D., Guo, R., Wen, Y., Liu, G., Chen, E.: Locating and mitigating gender bias in large language models (2024). arXiv:2403.14409","DOI":"10.1007\/978-981-97-5672-8_40"},{"key":"40_CR40","doi-asserted-by":"crossref","unstructured":"Cai, Y., Cao, D., Guo, R., Wen, Y., Liu, G., Chen, E.: Editing knowledge representation of language model via rephrased prefix prompts (2024). arXiv:2403.14381","DOI":"10.1007\/978-981-97-5672-8_39"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5672-8_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T14:23:19Z","timestamp":1726669399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5672-8_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756711","9789819756728"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5672-8_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}