{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T11:30:42Z","timestamp":1787743842388,"version":"build-2784847793"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060778","type":"print"},{"value":"9783032060785","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"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\/978-3-032-06078-5_15","type":"book-chapter","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T18:51:01Z","timestamp":1759171861000},"page":"257-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Pareto Multi-objective Alignment for\u00a0Language Models"],"prefix":"10.1007","author":[{"given":"Qiang","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Setareh","family":"Maghsudi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Alegre, L.N., Bazzan, A.L., Roijers, D.M., Now\u00e9, A., da\u00a0Silva, B.C.: Sample-efficient multi-objective learning via generalized policy improvement prioritization. arXiv preprint arXiv:2301.07784 (2023)","DOI":"10.65109\/TBSX2832"},{"key":"15_CR2","doi-asserted-by":"publisher","unstructured":"Bai, Y., Jones, A., Ndousse, K., et\u00a0al.: Training a helpful and harmless assistant with reinforcement learning from human feedback. CoRR abs\/2204.05862 (2022). https:\/\/doi.org\/10.48550\/ARXIV.2204.05862","DOI":"10.48550\/ARXIV.2204.05862"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Boyd, S.P., Vandenberghe, L.: Convex Optimization. Cambridge University Press (2004)","DOI":"10.1017\/CBO9780511804441"},{"key":"15_CR4","unstructured":"D\u00e9sid\u00e9ri, J.A.: Multiple-Gradient Descent Algorithm (MGDA). Research Report RR-6953 (2009)"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the NAACL-HLT 2019, pp. 4171\u20134186. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"15_CR6","unstructured":"Dubey, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Felten, F., Alegre, L.N., et\u00a0al.: A toolkit for reliable benchmarking and research in multi-objective reinforcement learning. In: Proceedings of the 37th Conference on Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1028"},{"key":"15_CR8","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1613\/JAIR.1.15702","volume":"79","author":"F Felten","year":"2024","unstructured":"Felten, F., Talbi, E., Danoy, G.: Multi-objective reinforcement learning based on decomposition: a taxonomy and framework. J. Artif. Intell. Res. 79, 679\u2013723 (2024). https:\/\/doi.org\/10.1613\/JAIR.1.15702","journal-title":"J. Artif. Intell. Res."},{"key":"15_CR9","unstructured":"Guo, D., et\u00a0al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"15_CR10","doi-asserted-by":"publisher","unstructured":"He, Q., Su, H., Zhang, J., Hou, X.: Frustratingly easy regularization on representation can boost deep reinforcement learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17\u201324, 2023, pp. 20215\u201320225. IEEE (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01936","DOI":"10.1109\/CVPR52729.2023.01936"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"He, Q., Yang, Y., Zhou, T., Fang, M., Maghsudi, S.: One model for all: multi-objective controllable language models (2025)","DOI":"10.1007\/978-3-032-06078-5_15"},{"key":"15_CR12","unstructured":"He, Q., Zhou, T., Fang, M., Maghsudi, S.: Adaptive regularization of representation rank as an implicit constraint of bellman equation. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7\u201311, 2024, OpenReview.net (2024). https:\/\/openreview.net\/forum?id=apXtolxDaJ"},{"key":"15_CR13","unstructured":"Ilyas, A., Engstrom, L., et\u00a0al.: A closer look at deep policy gradients. In: 8th International Conference on Learning Representations, Addis Ababa, Ethiopia, April 26-30, 2020, OpenReview.net (2020)"},{"key":"15_CR14","unstructured":"Liu, B., Liu, X., Jin, X., Stone, P., Liu, Q.: Conflict-averse gradient descent for multi-task learning. In: Annual Conference on Neural Information Processing Systems 2021. NeurIPS 2021, pp. 18878\u201318890 (2021)"},{"key":"15_CR15","unstructured":"Lu, H., Herman, D., Yu, Y.: Multi-objective reinforcement learning: convexity, stationarity and pareto optimality. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023. OpenReview.net (2023)"},{"key":"15_CR16","unstructured":"Maas, A.L., Daly, R.E., et\u00a0al.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, pp. 142\u2013150. Association for Computational Linguistics (2011)"},{"issue":"1","key":"15_CR17","first-page":"3483","volume":"15","author":"KV Moffaert","year":"2014","unstructured":"Moffaert, K.V., Now\u00e9, A.: Multi-objective reinforcement learning using sets of pareto dominating policies. J. Mach. Learn. Res. 15(1), 3483\u20133512 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"15_CR18","doi-asserted-by":"publisher","unstructured":"OpenAI: GPT-4 technical report. CoRR abs\/2303.08774 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.08774","DOI":"10.48550\/ARXIV.2303.08774"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Ouyang, L., Wu, J., Jiang, X., et\u00a0al.: Training language models to follow instructions with human feedback. In: Annual Conference on Neural Information Processing Systems 2022, New Orleans, LA, USA (2022)","DOI":"10.52202\/068431-2011"},{"key":"15_CR20","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Ram\u00e9, A., Couairon, G., Dancette, C., et\u00a0al.: Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. In: Annual Conference on Neural Information Processing Systems 2023, New Orleans, LA, USA (2023)","DOI":"10.52202\/075280-3114"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Reymond, M., Bargiacchi, E., Now\u00e9, A.: Pareto conditioned networks. In: 21st International Conference on Autonomous Agents and Multiagent Systems, Auckland, New Zealand, May 9\u201313, 2022, pp. 1110\u20131118 (2022)","DOI":"10.65109\/NPXB3014"},{"key":"15_CR23","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs\/1707.06347 (2017)"},{"key":"15_CR24","unstructured":"Sener, O., Koltun, V.: Multi-task learning as multi-objective optimization. In: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, Montr\u00e9al, Canada, pp. 525\u2013536 (2018)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Senushkin, D., Patakin, N., Kuznetsov, A., Konushin, A.: Independent component alignment for multi-task learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, pp. 20083\u201320093. IEEE (2023)","DOI":"10.1109\/CVPR52729.2023.01923"},{"key":"15_CR26","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Van\u00a0Moffaert, K., Drugan, M.M., Now\u00e9, A.: Scalarized multi-objective reinforcement learning: novel design techniques. In: 2013 IEEE Symposium on ADPRL, pp. 191\u2013199 (2013)","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"15_CR28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. In: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA, pp. 5998\u20136008 (2017)"},{"key":"15_CR29","unstructured":"von Werra, L., et al.: TRL: transformer reinforcement learning (2020). https:\/\/github.com\/huggingface\/trl"},{"key":"15_CR30","unstructured":"Yang, R., Pan, X., Luo, F., et\u00a0al.: Rewards-in-context: multi-objective alignment of foundation models with dynamic preference adjustment. In: Forty-first International Conference on Machine Learning, Vienna, Austria, July 21\u201327, 2024. OpenReview.net (2024)"},{"key":"15_CR31","unstructured":"Yang, R., Sun, X., Narasimhan, K.: A generalized algorithm for multi-objective reinforcement learning and policy adaptation. In: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, BC, Canada, pp. 14610\u201314621 (2019)"},{"key":"15_CR32","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. In: Annual Conference on Neural Information Processing Systems 2020. NeurIPS 2020, virtual (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06078-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:18:09Z","timestamp":1787703489000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06078-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"ISBN":["9783032060778","9783032060785"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06078-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,30]]},"assertion":[{"value":"30 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}