{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:02:37Z","timestamp":1757624557895,"version":"3.44.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045485","type":"print"},{"value":"9783032045492","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"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\/978-3-032-04549-2_28","type":"book-chapter","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T13:48:04Z","timestamp":1757425684000},"page":"343-355","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PGD: Probe Guided Decoding for\u00a0Alignment"],"prefix":"10.1007","author":[{"given":"Changxin","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"key":"28_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"28_CR2","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"28_CR3","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":"28_CR4","unstructured":"Dubois, Y., et al.: Alpacafarm: a simulation framework for methods that learn from human feedback. Adv. Neural Inf. Process. Syst.\u00a036 (2024)"},{"key":"28_CR5","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging llm-as-a-judge with mt-bench and chatbot arena. Adv. Neural Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Gao, M.,\u00a0Hu, X.,\u00a0Ruan, J.,\u00a0Pu, X.,\u00a0Wan, X.: Llm-based nlg evaluation: current status and challenges. arXiv preprint arXiv:2402.01383 (2024)","DOI":"10.1162\/coli_a_00561"},{"key":"28_CR7","unstructured":"Huang, H., et al.: On the limitations of fine-tuned judge models for llm evaluation. arXiv preprint arXiv:2403.02839 (2024)"},{"key":"28_CR8","unstructured":"Li, J.,\u00a0Sun, S.,\u00a0Yuan, W., Fan, R.-Z.,\u00a0Zhao, H.,\u00a0Liu, P.: Generative judge for evaluating alignment. arXiv preprint arXiv:2310.05470 (2023)"},{"key":"28_CR9","unstructured":"Zhu, L.,\u00a0Wang, X.,\u00a0Wang, X.: Judgelm: fine-tuned large language models are scalable judges. arXiv preprint arXiv:2310.17631 (2023)"},{"key":"28_CR10","unstructured":"Wang, Y., et\u00a0al.: Pandalm: an automatic evaluation benchmark for llm instruction tuning optimization. arXiv preprint arXiv:2306.05087 (2023)"},{"key":"28_CR11","unstructured":"Kim, S., et\u00a0al.: Prometheus: inducing fine-grained evaluation capability in language models. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"Kim, S., et al.: Prometheus 2: an open source language model specialized in evaluating other language models. arXiv preprint arXiv:2405.01535 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.248"},{"key":"28_CR13","doi-asserted-by":"crossref","unstructured":"Tenney, I.: Bert rediscovers the classical nlp pipeline. arXiv preprint arXiv:1905.05950 (2019)","DOI":"10.18653\/v1\/P19-1452"},{"key":"28_CR14","unstructured":"Dubey, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"28_CR15","unstructured":"Rafailov, R.,\u00a0Sharma, A.,\u00a0Mitchell, E., Manning, C.D.,\u00a0Ermon, S.,\u00a0Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural Inf. Process. Syst.\u00a036 (2024)"},{"key":"28_CR16","unstructured":"Li, K.,\u00a0Patel, O.,\u00a0Vi\u00e9gas, F.,\u00a0Pfister, H.,\u00a0Wattenberg, M.: Inference-time intervention: eliciting truthful answers from a language model. Adv. Neural Inf. Process. Syst.\u00a036 (2024)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"White, J.C.,\u00a0Pimentel, T.,\u00a0Saphra, N.,\u00a0Cotterell, R.: A non-linear structural probe. arXiv preprint arXiv:2105.10185 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.12"},{"key":"28_CR18","unstructured":"Li, X.L., et al.: Contrastive decoding: open-ended text generation as optimization. arXiv preprint arXiv:2210.15097 (2022)"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Chaffin, A.,\u00a0Claveau, V.,\u00a0Kijak, E.: Ppl-mcts: constrained textual generation through discriminator-guided mcts decoding. arXiv preprint arXiv:2109.13582 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.215"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Deng, H.,\u00a0Raffel, C.: Reward-augmented decoding: efficient controlled text generation with a unidirectional reward model. arXiv preprint arXiv:2310.09520 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.721"},{"key":"28_CR21","unstructured":"Khanov, M.,\u00a0Burapacheep, J.,\u00a0Li, Y.: Args: alignment as reward-guided search. arXiv preprint arXiv:2402.01694 (2024)"},{"key":"28_CR22","first-page":"9236","volume":"2024","author":"J Yi","year":"2024","unstructured":"Yi, J., et al.: On the vulnerability of safety alignment in open-access llms. Find. Assoc. Comput. Linguist. ACL 2024, 9236\u20139260 (2024)","journal-title":"Find. Assoc. Comput. Linguist. ACL"},{"key":"28_CR23","unstructured":"Vaswani, A.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2017)"},{"key":"28_CR24","unstructured":"Zeng, Z.,\u00a0Yu, J.,\u00a0Gao, T.,\u00a0Meng, Y.,\u00a0Goyal, T.,\u00a0Chen, D.: Evaluating large language models at evaluating instruction following. arXiv preprint arXiv:2310.07641 (2023)"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Saha, S.,\u00a0Levy, O.,\u00a0Celikyilmaz, A.,\u00a0Bansal, M.,\u00a0Weston, J.,\u00a0Li, X.: Branch-solve-merge improves large language model evaluation and generation. arXiv preprint arXiv:2310.15123 (2023)","DOI":"10.18653\/v1\/2024.naacl-long.462"},{"key":"28_CR26","unstructured":"Team, Q.: Qwen2.5: a party of foundation models (2024). https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"28_CR27","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04549-2_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T13:48:17Z","timestamp":1757425697000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04549-2_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"ISBN":["9783032045485","9783032045492"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04549-2_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"assertion":[{"value":"10 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}