{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T02:32:30Z","timestamp":1777861950929,"version":"3.51.4"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031971402","type":"print"},{"value":"9783031971419","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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\/978-3-031-97141-9_8","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T08:57:53Z","timestamp":1751273873000},"page":"111-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explaining Bias in\u00a0Internal Representations of\u00a0Large Language Models via\u00a0Concept Activation Vectors"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4510-0975","authenticated-orcid":false,"given":"Jasper Kyle","family":"Catapang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Baly, R., San\u00a0Martino, G.D., Glass, J., Nakov, P.: We can detect your bias: predicting the political ideology of news articles. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4982\u20134991 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.404"},{"issue":"4","key":"8_CR2","doi-asserted-by":"publisher","first-page":"991","DOI":"10.1257\/0002828042002561","volume":"94","author":"M Bertrand","year":"2004","unstructured":"Bertrand, M., Mullainathan, S.: Are emily and greg more employable than lakisha and jamal? A field experiment on labor market discrimination. Am. Econ. Rev. 94(4), 991\u20131013 (2004)","journal-title":"Am. Econ. Rev."},{"key":"8_CR3","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)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Dinan, E., Fan, A., Wu, L., Weston, J., Kiela, D., Williams, A.: Multi-dimensional gender bias classification. In: Proceedings of EMNLP 2020, pp. 314\u2013331 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.23"},{"key":"8_CR5","unstructured":"Dong, X., Wang, Y., Yu, P.S., Caverlee, J.: Probing explicit and implicit gender bias through llm conditional text generation. arXiv preprint arXiv:2311.00306 (2023)"},{"key":"8_CR6","unstructured":"Dong, X., Wang, Y., Yu, P.S., Caverlee, J.: Disclosure and mitigation of gender bias in llms. arXiv preprint arXiv:2402.11190 (2024)"},{"key":"8_CR7","unstructured":"Jones, C.: Political bias dataset: a synthetic dataset for bias detection and reduction (2024). https:\/\/huggingface.co\/datasets\/cajcodes\/political-bias"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Kotek, H., Dockum, R., Sun, D.: Gender bias and stereotypes in large language models. In: Proceedings of the ACM Collective Intelligence Conference, pp. 12\u201324 (2023)","DOI":"10.1145\/3582269.3615599"},{"key":"8_CR9","unstructured":"Kumar, S.H., et al.: Decoding biases: automated methods and llm judges for gender bias detection in language models. arXiv preprint arXiv:2408.03907 (2024)"},{"key":"8_CR10","doi-asserted-by":"publisher","unstructured":"Li, B., Wisniewski, G.: Are neural networks extracting linguistic properties or memorizing training data? An observation with a multilingual probe for predicting tense. In: Merlo, P., Tiedemann, J., Tsarfaty, R. (eds.) Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 3080\u20133089. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.eacl-main.269. https:\/\/aclanthology.org\/2021.eacl-main.269\/","DOI":"10.18653\/v1\/2021.eacl-main.269"},{"key":"8_CR11","unstructured":"Li, T., et\u00a0al.: Rethinking jailbreaking through the lens of representation engineering. arXiv preprint arXiv:2401.06824 (2024)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Masoudian, S., Frohmann, M., Rekabsaz, N., Schedl, M.: Unlabeled debiasing in downstream tasks via class-wise low variance regularization. arXiv preprint arXiv:2409.19541 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.612"},{"key":"8_CR13","doi-asserted-by":"publisher","unstructured":"Mendelson, M., Belinkov, Y.: Debiasing methods in natural language understanding make bias more accessible. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 1545\u20131557. Association for Computational Linguistics, Online and Punta Cana (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.116. https:\/\/aclanthology.org\/2021.emnlp-main.116\/","DOI":"10.18653\/v1\/2021.emnlp-main.116"},{"issue":"41","key":"8_CR14","doi-asserted-by":"publisher","first-page":"16474","DOI":"10.1073\/pnas.1211286109","volume":"109","author":"CA Moss-Racusin","year":"2012","unstructured":"Moss-Racusin, C.A., Dovidio, J.F., Brescoll, V.L., Graham, M.J., Handelsman, J.: Science faculty\u2019s subtle gender biases favor male students. Proc. Natl. Acad. Sci. 109(41), 16474\u201316479 (2012)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Nadeem, M., Bethke, A., Reddy, S.: Stereoset: measuring stereotypical bias in pretrained language models. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL), pp. 5356\u20135371. Association for Computational Linguistics (2021). https:\/\/aclanthology.org\/2021.acl-long.416","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"8_CR16","first-page":"116743","volume":"37","author":"Z Xu","year":"2025","unstructured":"Xu, Z., Huang, R., Chen, C., Wang, X.: Uncovering safety risks of large language models through concept activation vector. Adv. Neural. Inf. Process. Syst. 37, 116743\u2013116782 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Zheng, X., Jiang, J.: An empirical study of memorization in nlp. arXiv preprint arXiv:2203.12171 (2022)","DOI":"10.18653\/v1\/2022.acl-long.434"},{"key":"8_CR18","unstructured":"Zou, A., Wang, L., et\u00a0al.: Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043 (2023)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97141-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T05:05:39Z","timestamp":1777525539000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97141-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"ISBN":["9783031971402","9783031971419"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97141-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"assertion":[{"value":"1 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kanazawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"4 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/nldb2025.github.io\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}