{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T09:29:14Z","timestamp":1769938154821,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819549689","type":"print"},{"value":"9789819549696","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"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\/978-981-95-4969-6_17","type":"book-chapter","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T08:48:42Z","timestamp":1763974122000},"page":"220-232","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Concept Control for\u00a0LLM Safety Using Radial Basis Function Representations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3399-6100","authenticated-orcid":false,"given":"Mark","family":"Amos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1283-1672","authenticated-orcid":false,"given":"Yang","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7712-6646","authenticated-orcid":false,"given":"Maurice","family":"Pagnucco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,25]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Bender, E.M., Gebru, T., McMillan-Major, A., Shmitchell, S.: On the dangers of stochastic parrots: can language models be too big? In: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, pp. 610\u2013623 (2021)","DOI":"10.1145\/3442188.3445922"},{"key":"17_CR2","unstructured":"Broomhead, D.S., Lowe, D.: Radial basis functions, multi-variable functional interpolation and adaptive networks. Technical report, Royal Signals and Radar Establishment (1988)"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Dhamala, J., et\u00a0al.: BOLD: dataset and metrics for measuring biases in open-ended language generation. In: ACM FAccT 2021 (2021)","DOI":"10.1145\/3442188.3445924"},{"key":"17_CR4","unstructured":"Durbin, J.: Truthy DPO. Online (2023). https:\/\/huggingface.co\/datasets\/jondurbin\/truthy-dpo-v0.1"},{"key":"17_CR5","unstructured":"Elhage, N., et\u00a0al.: A mathematical framework for transformer circuits. Transformer Circuits Thread (2021). https:\/\/transformer-circuits.pub\/2021\/framework\/index.html"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Garrido-Mu\u00f1oz, I., Montejo-R\u00e1ez, A., Mart\u00ednez-Santiago, F., Ure\u00f1a-L\u00f3pez, L.A.: A survey on bias in deep NLP. Appl. Sci. 11(7) (2021)","DOI":"10.3390\/app11073184"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Gehman, S., Gururangan, S., Sap, M., Choi, Y., Smith, N.A.: RealToxicityPrompts: evaluating neural toxic degeneration in language models. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 3356\u20133369 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"17_CR8","unstructured":"Ghorbani, A., Wexler, J., Zou, J.Y., Kim, B.: Towards automatic concept-based explanations. In: Advances in Neural Information Processing Systems, vol.\u00a032 (2019)"},{"key":"17_CR9","unstructured":"Hanna, M., Liu, O., Variengien, A.: How does GPT-2 compute greater-than?: interpreting mathematical abilities in a pre-trained language model. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 76033\u201376060 (2023)"},{"key":"17_CR10","unstructured":"Hu, E.J., et\u00a0al.: LoRA: low-rank adaptation of large language models. In: International Conference on Learning Representations (2022)"},{"key":"17_CR11","unstructured":"Jiang, A.Q., et\u00a0al.: Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Leong, C.T., Cheng, Y., Wang, J., Wang, J., Li, W.: Self-detoxifying language models via toxification reversal. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 4433\u20134449 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.269"},{"key":"17_CR13","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR14","unstructured":"Liang, P., et\u00a0al.: Holistic evaluation of language models. Trans. Mach. Learn. Res. (2023)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Lin, S., Hilton, J., Evans, O.: TruthfulQA: measuring how models mimic human falsehoods. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3214\u20133252 (2022)","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"17_CR16","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS 2017, pp. 4768\u20134777 (2017)"},{"key":"17_CR17","unstructured":"Marks, S., Tegmark, M.: The geometry of truth: emergent linear structure in large language model representations of true\/false datasets. In: First Conference on Language Modeling (2024)"},{"issue":"309","key":"17_CR18","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1080\/01621459.1965.10480787","volume":"60","author":"WF Massy","year":"1965","unstructured":"Massy, W.F.: Principal components regression in exploratory statistical research. J. Am. Stat. Assoc. 60(309), 234\u2013256 (1965)","journal-title":"J. Am. Stat. Assoc."},{"issue":"1","key":"17_CR19","first-page":"5","volume":"8","author":"SJ Miller","year":"2006","unstructured":"Miller, S.J.: The method of least squares. Mathematics Department Brown University 8(1), 5\u201311 (2006)","journal-title":"Mathematics Department Brown University"},{"key":"17_CR20","unstructured":"Olsson, C., et\u00a0al.: In-context learning and induction heads. Transformer Circuits Thread (2022). https:\/\/transformer-circuits.pub\/2022\/in-context-learning-and-induction-heads\/index.html"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Parrish, A., et\u00a0al.: 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":"17_CR22","doi-asserted-by":"crossref","unstructured":"Pearson, K.: Liii. on lines and planes of closest fit to systems of points in space. London Edinburgh Dublin Philos. Mag. J. Sci. 2(11), 559\u2013572 (1901)","DOI":"10.1080\/14786440109462720"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Perlitz, Y., et\u00a0al.: Efficient benchmarking (of language models). In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 2519\u20132536 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.139"},{"key":"17_CR24","unstructured":"Rafailov, R., et\u00a0al.: Direct preference optimization: your language model is secretly a reward model. In: Advances in Neural Information Processing Systems, vol.\u00a036, pp. 53728\u201353741 (2023)"},{"issue":"4","key":"17_CR25","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1023\/A:1008202821328","volume":"11","author":"R Storn","year":"1997","unstructured":"Storn, R., Price, K.: Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11(4), 341\u2013359 (1997)","journal-title":"J. Global Optim."},{"key":"17_CR26","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a070, pp. 3319\u20133328 (2017)"},{"key":"17_CR27","unstructured":"Turner, A.M., et\u00a0al.: Activation addition: steering language models without optimization. arXiv preprint arXiv:2308.10248 (2024)"},{"key":"17_CR28","unstructured":"Vijayakumar, A.K., et\u00a0al.: Diverse beam search: decoding diverse solutions from neural sequence models. arXiv preprint arXiv:1610.02424 (2018)"},{"key":"17_CR29","unstructured":"Virtanen, P., et\u00a0al.: SciPy 1.0: fundamental algorithms for scientific computing in python. Nat. Methods 17, 261\u2013272 (2020)"},{"key":"17_CR30","unstructured":"Zarlenga, M.E., et\u00a0al.: Concept embedding models: beyond the accuracy-explainability trade-off. In: Advances in Neural Information Processing Systems, vol.\u00a035, pp. 21400\u201321413 (2022)"},{"key":"17_CR31","unstructured":"Zou, A., et\u00a0al.: Representation engineering: a top-down approach to AI transparency. arXiv preprint arXiv:2310.01405 (2023)"}],"container-title":["Lecture Notes in Computer Science","AI 2025: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4969-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T20:57:41Z","timestamp":1769893061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4969-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"ISBN":["9789819549689","9789819549696"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4969-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,25]]},"assertion":[{"value":"25 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canberra, ACT","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"1 December 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}