{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:57:29Z","timestamp":1781161049306,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819200672","type":"print"},{"value":"9789819200689","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-92-0068-9_10","type":"book-chapter","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:10:03Z","timestamp":1781158203000},"page":"136-150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of\u00a0DPO Configurations for\u00a0LLM Alignment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0246-0819","authenticated-orcid":false,"given":"Jan","family":"Majkutewicz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5029-6768","authenticated-orcid":false,"given":"Julian","family":"Szyma\u0144ski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","unstructured":"Aakanksha, Ahmadian, A., Goldfarb-Tarrant, S., Ermis, B., Fadaee, M., Hooker, S.: Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning (2024). https:\/\/doi.org\/10.48550\/arXiv.2410.10801","DOI":"10.48550\/arXiv.2410.10801"},{"key":"10_CR2","doi-asserted-by":"publisher","unstructured":"Askell, A., et al.: A General Language Assistant as a Laboratory for Alignment (2021). https:\/\/doi.org\/10.48550\/arXiv.2112.00861","DOI":"10.48550\/arXiv.2112.00861"},{"key":"10_CR3","doi-asserted-by":"publisher","unstructured":"Azar, M.G., et al.: A General Theoretical Paradigm to Understand Learning from Human Preferences (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.12036","DOI":"10.48550\/arXiv.2310.12036"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Bai, G., Liu, J., Bu, X., He, Y., Liu, J., et\u00a0al.: MT-Bench-101: a fine-grained benchmark for evaluating large language models in multi-turn dialogues. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 7421\u20137454 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.401","DOI":"10.18653\/v1\/2024.acl-long.401"},{"key":"10_CR5","doi-asserted-by":"publisher","unstructured":"Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., et\u00a0al.: Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback (2022). https:\/\/doi.org\/10.48550\/arXiv.2204.05862","DOI":"10.48550\/arXiv.2204.05862"},{"key":"10_CR6","doi-asserted-by":"publisher","unstructured":"Cui, G., Yuan, L., Ding, N., Yao, G., He, B., et\u00a0al.: UltraFeedback: Boosting Language Models with Scaled AI Feedback (2024). https:\/\/doi.org\/10.48550\/arXiv.2310.01377","DOI":"10.48550\/arXiv.2310.01377"},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Cui, J., Chiang, W.L., Stoica, I., Hsieh, C.J.: OR-Bench: An Over-Refusal Benchmark for Large Language Models (2025). https:\/\/doi.org\/10.48550\/arXiv.2405.20947","DOI":"10.48550\/arXiv.2405.20947"},{"key":"10_CR8","doi-asserted-by":"publisher","unstructured":"Dubois, Y., Galambosi, B., Liang, P., Hashimoto, T.B.: Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators (2025). https:\/\/doi.org\/10.48550\/arXiv.2404.04475","DOI":"10.48550\/arXiv.2404.04475"},{"key":"10_CR9","doi-asserted-by":"publisher","unstructured":"Ethayarajh, K., Xu, W., Muennighoff, N., Jurafsky, D., Kiela, D.: KTO: Model Alignment as Prospect Theoretic Optimization (2024). https:\/\/doi.org\/10.48550\/arXiv.2402.01306","DOI":"10.48550\/arXiv.2402.01306"},{"key":"10_CR10","doi-asserted-by":"publisher","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., et\u00a0al.: The Llama 3 Herd of Models (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.21783","DOI":"10.48550\/arXiv.2407.21783"},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Hammoud, H.A.A.K., et al.: Model Merging and Safety Alignment: One Bad Model Spoils the Bunch (2024). https:\/\/doi.org\/10.48550\/arXiv.2406.14563","DOI":"10.48550\/arXiv.2406.14563"},{"key":"10_CR12","doi-asserted-by":"publisher","unstructured":"Ji, J., Hong, D., Zhang, B., Chen, B., Dai, J., et\u00a0al.: PKU-SafeRLHF: towards multi-level safety alignment for LLMs with human preference. In: Che, W., Nabende, J., Shutova, E., Pilehvar, M.T. (eds.) Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 31983\u201332016. Association for Computational Linguistics, Vienna, Austria (2025). https:\/\/doi.org\/10.18653\/v1\/2025.acl-long.1544","DOI":"10.18653\/v1\/2025.acl-long.1544"},{"key":"10_CR13","doi-asserted-by":"publisher","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D.S., et\u00a0al.: Mistral 7B (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.06825","DOI":"10.48550\/arXiv.2310.06825"},{"key":"10_CR14","doi-asserted-by":"publisher","unstructured":"K\u00f6pf, A., Kilcher, Y., von R\u00fctte, D., Anagnostidis, S., Tam, Z.R., et\u00a0al.: OpenAssistant Conversations \u2013 Democratizing Large Language Model Alignment (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.07327","DOI":"10.48550\/arXiv.2304.07327"},{"key":"10_CR15","doi-asserted-by":"publisher","unstructured":"Lambert, N., Morrison, J., Pyatkin, V., Huang, S., Ivison, H., et\u00a0al.: Tulu 3: Pushing Frontiers in Open Language Model Post-Training (2025). https:\/\/doi.org\/10.48550\/arXiv.2411.15124","DOI":"10.48550\/arXiv.2411.15124"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Lambert, N., Pyatkin, V., Morrison, J., Miranda, L.J., Lin, B.Y., et\u00a0al.: RewardBench: Evaluating Reward Models for Language Modeling (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.13787","DOI":"10.48550\/arXiv.2403.13787"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Majkutewicz, J., Szyma\u0144ski, J.: An integrated approach for prototyping and deploying large language models. In: Computer Information Systems and Industrial Management, pp. 179\u2013193. Springer, Cham (2026)","DOI":"10.1007\/978-3-032-02406-0_13"},{"key":"10_CR18","doi-asserted-by":"publisher","unstructured":"Morimura, T., Sakamoto, M., Jinnai, Y., Abe, K., Ariu, K.: Filtered Direct Preference Optimization (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.13846","DOI":"10.48550\/arXiv.2404.13846"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.02155","DOI":"10.48550\/arXiv.2203.02155"},{"key":"10_CR20","doi-asserted-by":"publisher","unstructured":"Pan, Y., Cai, Z., Chen, G., Zhong, H., Wang, C.: What Matters in Data for DPO? (2025). https:\/\/doi.org\/10.48550\/arXiv.2508.18312","DOI":"10.48550\/arXiv.2508.18312"},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"Park, R., Rafailov, R., Ermon, S., Finn, C.: Disentangling Length from Quality in Direct Preference Optimization (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.19159","DOI":"10.48550\/arXiv.2403.19159"},{"key":"10_CR22","doi-asserted-by":"publisher","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C.D., Finn, C.: Direct Preference Optimization: Your Language Model is Secretly a Reward Model (2024). https:\/\/doi.org\/10.48550\/arXiv.2305.18290","DOI":"10.48550\/arXiv.2305.18290"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"Ram\u00e9, A., et al.: Rewarded soups: Towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.04488","DOI":"10.48550\/arXiv.2306.04488"},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Shi, Z., Land, S., Locatelli, A., Geist, M., Bartolo, M.: Understanding Likelihood Over-optimisation in Direct Alignment Algorithms (2024). https:\/\/doi.org\/10.48550\/arXiv.2410.11677","DOI":"10.48550\/arXiv.2410.11677"},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Tunstall, L., Beeching, E., Lambert, N., Rajani, N., Rasul, K., et\u00a0al.: Zephyr: Direct Distillation of LM Alignment (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.16944","DOI":"10.48550\/arXiv.2310.16944"},{"key":"10_CR26","doi-asserted-by":"publisher","unstructured":"Wortsman, M., et al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.05482","DOI":"10.48550\/arXiv.2203.05482"},{"key":"10_CR27","doi-asserted-by":"publisher","unstructured":"Wu, J., et al.: $${\\beta }$$ -DPO: Direct Preference Optimization with Dynamic $${\\beta }$$ (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.08639","DOI":"10.48550\/arXiv.2407.08639"},{"key":"10_CR28","doi-asserted-by":"publisher","unstructured":"Xie, T., Qi, X., Zeng, Y., Huang, Y., Sehwag, U.M., et\u00a0al.: SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal (2025). https:\/\/doi.org\/10.48550\/arXiv.2406.14598","DOI":"10.48550\/arXiv.2406.14598"},{"key":"10_CR29","doi-asserted-by":"publisher","unstructured":"Yadav, P., Tam, D., Choshen, L., Raffel, C., Bansal, M.: TIES-Merging: Resolving Interference When Merging Models (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.01708","DOI":"10.48550\/arXiv.2306.01708"},{"key":"10_CR30","doi-asserted-by":"publisher","unstructured":"Yang, J., et al.: Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging (2025). https:\/\/doi.org\/10.48550\/arXiv.2502.06876","DOI":"10.48550\/arXiv.2502.06876"},{"key":"10_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112701","volume":"306","author":"X Yi","year":"2024","unstructured":"Yi, X., Zheng, S., Wang, L., Wang, X., He, L.: A safety realignment framework via subspace-oriented model fusion for large language models. Knowl.-Based Syst. 306, 112701 (2024). https:\/\/doi.org\/10.1016\/j.knosys.2024.112701","journal-title":"Knowl.-Based Syst."},{"key":"10_CR32","doi-asserted-by":"publisher","unstructured":"Yu, L., Yu, B., Yu, H., Huang, F., Li, Y.: Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch (2024). https:\/\/doi.org\/10.48550\/arXiv.2311.03099","DOI":"10.48550\/arXiv.2311.03099"},{"key":"10_CR33","doi-asserted-by":"publisher","unstructured":"Zhou, Z., et al.: Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization (2024). https:\/\/doi.org\/10.48550\/arXiv.2310.03708","DOI":"10.48550\/arXiv.2310.03708"}],"container-title":["Communications in Computer and Information Science","Recent Challenges in Intelligent information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-0068-9_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:10:12Z","timestamp":1781158212000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-0068-9_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819200672","9789819200689"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-0068-9_10","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare relevant to this article\u2019s content.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaohsiung","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","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":"13 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}