{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T09:08:51Z","timestamp":1784365731312,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234226","type":"print"},{"value":"9789819234233","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3423-3_26","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T08:45:25Z","timestamp":1784364325000},"page":"318-330","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-layer Representation Editing for Rejection Behavior Control in Large Language Models"],"prefix":"10.1007","author":[{"given":"Wei","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuoyoucheng","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanying","family":"Tong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"26_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Wei, A., Haghtalab, N., Steinhardt, J.: Jailbroken: How does LLM safety training fail? In: Advances in Neural Information Processing Systems, vol. 36, pp. 80079\u201380110 (2023)","DOI":"10.52202\/075280-3508"},{"key":"26_CR3","unstructured":"Jain, N., Schwarzschild, A., Wen, Y., et al.: Baseline defenses for adversarial attacks against aligned language models. arXiv preprint arXiv:2309.00614 (2023)"},{"key":"26_CR4","unstructured":"Lermen, S., Rogers-Smith, C., Ladish, J.: Lora fine-tuning efficiently undoes safety training in Llama 2-chat 70b. arXiv preprint arXiv:2310.20624 (2023)"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Xu, Z., Jiang, F., Niu, L., et al.: SafeDecoding: Defending against jailbreak attacks via safety-aware decoding. arXiv preprint arXiv:2402.08983 (2024)","DOI":"10.18653\/v1\/2024.acl-long.303"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Arditi, A., Obeso, O., Syed, A., et al.: Refusal in language models is mediated by a single direction. In: Advances in Neural Information Processing Systems, vol. 37, pp. 136037\u2013136083 (2024)","DOI":"10.52202\/079017-4322"},{"key":"26_CR7","unstructured":"Zou, A., Phan, L., Chen, S., et al.: Representation engineering: A top-down approach to AI transparency. arXiv preprint arXiv:2310.01405 (2023)"},{"issue":"4","key":"26_CR8","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1023\/A:1008306431147","volume":"13","author":"DR Jones","year":"1998","unstructured":"Jones, D.R., Schonlau, M., Welch, W.J.: Efficient global optimization of expensive black-box functions. J. Global Optim. 13(4), 455\u2013492 (1998)","journal-title":"J. Global Optim."},{"key":"26_CR9","unstructured":"Touvron, H., Martin, L., Stone, K., et al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"26_CR10","unstructured":"Team, G., Mesnard, T., Hardin, C., et al.: Gemma: Open models based on Gemini research and technology. arXiv preprint arXiv:2403.08295 (2024)"},{"key":"26_CR11","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A., et al.: Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"26_CR12","unstructured":"Team, Q.: Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)"},{"key":"26_CR13","unstructured":"Hendrycks, D., Burns, C., Basart, S., et al.: Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)"},{"key":"26_CR14","unstructured":"Cobbe, K., Kosaraju, V., Bavarian, M., et al.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"},{"key":"26_CR15","unstructured":"Wei, Z., Wang, Y., Li, A., et al.: Jailbreak and guard aligned language models with only few in-context demonstrations. arXiv preprint arXiv:2310.06387 (2023)"},{"key":"26_CR16","unstructured":"Phute, M., Helbling, A., Hull, M., et al.: LLM self defense: By self examination, LLMs know they are being tricked. arXiv preprint arXiv:2308.07308 (2023)"},{"key":"26_CR17","unstructured":"Wei, J., Bosma, M., Zhao, V.Y., et al.: Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2021)"},{"key":"26_CR18","unstructured":"Bai, Y., Jones, A., Ndousse, K., et al.: Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Jin, Z., He, G.: Safeguarding system prompts for LLMs. arXiv preprint arXiv:2412.13426 (2024)","DOI":"10.18653\/v1\/2025.findings-emnlp.147"},{"key":"26_CR20","unstructured":"Lee, S., Ni, S., Wei, C., et al.: xJailbreak: Representation space guided reinforcement learning for interpretable LLM jailbreaking. arXiv preprint arXiv:2501.16727 (2025)"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Lin, Y., He, P., Xu, H., et al.: Towards understanding jailbreak attacks in LLMs: A representation space analysis. arXiv preprint arXiv:2406.10794 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.401"},{"key":"26_CR22","unstructured":"Turner, A.M., Thiergart, L., Leech, G., et al.: Steering language models with activation engineering. arXiv preprint arXiv:2308.10248 (2023)"},{"key":"26_CR23","unstructured":"Taori, R., Gulrajani, I., Zhang, T., et al.: Stanford Alpaca: An instruction-following Llama model (2023)"},{"key":"26_CR24","unstructured":"Zou, A., Wang, Z., Carlini, N., et al.: Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043 (2023)"},{"key":"26_CR25","unstructured":"Qi, X., Zeng, Y., Xie, T., et al.: Fine-tuning aligned language models compromises safety, even when users do not intend to! arXiv preprint arXiv:2310.03693 (2023)"},{"key":"26_CR26","unstructured":"Inan, H., Upasani, K., Chi, J., et al.: Llama guard: LLM-based input-output safeguard for human-AI conversations. arXiv preprint arXiv:2312.06674 (2023)"},{"key":"26_CR27","unstructured":"Clark, P., Cowhey, I., Etzioni, O., et al.: Think you have solved question answering? Try ARC, the AI2 reasoning challenge. arXiv preprint arXiv:1803.05457 (2018)"},{"key":"26_CR28","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"}],"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\/978-981-92-3423-3_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T08:45:26Z","timestamp":1784364326000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3423-3_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819234226","9789819234233"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3423-3_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 July 2026","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":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","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":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}