{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:54:19Z","timestamp":1763790859134,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533459","type":"print"},{"value":"9789819533466","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"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\/978-981-95-3346-6_13","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:50:08Z","timestamp":1763790608000},"page":"168-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Latent Feature Activation Steering for\u00a0Enhancing Semantic Consistency in\u00a0Large Language Models"],"prefix":"10.1007","author":[{"given":"Jingyuan","family":"Yang","sequence":"first","affiliation":[]},{"given":"Rongjun","family":"Li","sequence":"additional","affiliation":[]},{"given":"Weixuan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ziyu","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Zhiyong","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Peng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"issue":"4","key":"13_CR1","doi-asserted-by":"publisher","first-page":"2775","DOI":"10.1137\/140979861","volume":"26","author":"A Agarwal","year":"2016","unstructured":"Agarwal, A., Anandkumar, A., Jain, P., Netrapalli, P.: Learning sparsely used overcomplete dictionaries via alternating minimization. SIAM J. Optim. 26(4), 2775\u20132799 (2016)","journal-title":"SIAM J. Optim."},{"key":"13_CR2","unstructured":"Bricken, T., Templeton, A., Batson, J., Chen, B., Jermyn, A., Conerly, T., Turner, N., Anil, C., Denison, C., Askell, A., et\u00a0al.: Towards monosemanticity: Decomposing language models with dictionary learning. Transformer Circuits Thread 2 (2023)"},{"key":"13_CR3","unstructured":"Cunningham, H., Ewart, A., Riggs, L., Huben, R., Sharkey, L.: Sparse autoencoders find highly interpretable features in language models. arXiv preprint arXiv:2309.08600 (2023)"},{"key":"13_CR4","unstructured":"Elhage, N., et\u00a0al.: Toy models of superposition. arXiv preprint arXiv:2209.10652 (2022)"},{"key":"13_CR5","unstructured":"Fierro, C., Li, J., S\u00f8gaard, A.: Does instruction tuning make LLMs more consistent? arXiv preprint arXiv:2404.15206 (2024)"},{"key":"13_CR6","unstructured":"Gao, L., et al.: Scaling and evaluating sparse autoencoders. arXiv preprint arXiv:2406.04093 (2024)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Gu, J.C., et al.: Model editing harms general abilities of large language models: regularization to the rescue. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 16801\u201316819 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.934"},{"key":"13_CR8","unstructured":"Li, K., Patel, O., Vi\u00e9gas, F., Pfister, H., Wattenberg, M.: Inference-time intervention: eliciting truthful answers from a language model. arXiv preprint arXiv:2306.03341 (2023)"},{"key":"13_CR9","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., Kong, C., Liu, Y., Sun, M.: Fantastic semantics and where to find them: investigating which layers of generative LLMs reflect lexical semantics. arXiv preprint arXiv:2403.01509 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.866"},{"key":"13_CR11","unstructured":"Maas, A., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 142\u2013150 (2011)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cohen, S.B., Lapata, M.: Don\u2019t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization. arXiv abs\/1808.08745 (2018)","DOI":"10.18653\/v1\/D18-1206"},{"key":"13_CR13","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"13_CR14","unstructured":"Rabinovich, E., Ackerman, S., Raz, O., Farchi, E., Anaby-Tavor, A.: Predicting question-answering performance of large language models through semantic consistency (2023)"},{"key":"13_CR15","unstructured":"Raj, H., Gupta, V., Rosati, D., Majumdar, S.: Semantic consistency for assuring reliability of large language models. arXiv preprint arXiv:2308.09138 (2023)"},{"key":"13_CR16","unstructured":"Raj, H., Rosati, D., Majumdar, S.: Measuring reliability of large language models through semantic consistency. In: NeurIPS ML Safety Workshop (2022)"},{"key":"13_CR17","unstructured":"Rajamanoharan, S., et al.: Improving dictionary learning with gated sparse autoencoders. arXiv preprint arXiv:2404.16014 (2024)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Rimsky, N., Gabrieli, N., Schulz, J., Tong, M., Hubinger, E., Turner, A.: Steering llama 2 via contrastive activation addition. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15504\u201315522 (2024)","DOI":"10.18653\/v1\/2024.acl-long.828"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"See, A., Liu, P.J., Manning, C.D.: Get to the point: summarization with pointer-generator networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1073\u20131083 (2017)","DOI":"10.18653\/v1\/P17-1099"},{"key":"13_CR20","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"13_CR21","unstructured":"Turner, A.M., et al.: Activation addition: steering language models without optimization. arXiv e-prints pp. arXiv-2308 (2023)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Wang, W., Haddow, B., Birch, A., Peng, W.: Assessing factual reliability of large language model knowledge. 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. 805\u2013819 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.46"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Yang, J., Chen, D., Sun, Y., Li, R., Feng, Z., Peng, W.: Enhancing semantic consistency of large language models through model editing: an interpretability-oriented approach. In: Findings of the Association for Computational Linguistics ACL 2024, pp. 3343\u20133353 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.199"},{"key":"13_CR24","unstructured":"Zhang, X., Zhao, J.J., LeCun, Y.: Character-level convolutional networks for text classification. In: NIPS (2015)"},{"key":"13_CR25","unstructured":"Zhao, Y., et al.: Improving the robustness of large language models via consistency alignment. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 8931\u20138941 (2024)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3346-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:50:11Z","timestamp":1763790611000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3346-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533459","9789819533466"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3346-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}