{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/emorl-ensemble-multi-objective-reinforcement","title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning","arxiv_id":"2505.02579","date":"2025-05-05","proceeding":null,"authors":["Lingxiao Kong","Cong Yang","Susanne Neufang","Oya Deniz Beyan","Zeyd Boukhers"],"abstract":"Recent advances in reinforcement learning (RL) for large language model (LLM) fine-tuning show promise in addressing multi-objective tasks but still face significant challenges, including complex objective balancing, low training efficiency, poor scalability, and limited explainability. Leveraging ensemble learning principles, we introduce an Ensemble Multi-Objective RL (EMORL) framework that fine-tunes multiple models with individual objectives while optimizing their aggregation after the training to improve efficiency and flexibility. Our method is the first to aggregate the last hidden states of individual models, incorporating contextual information from multiple objectives. This approach is supported by a hierarchical grid search algorithm that identifies optimal weighted combinations. We evaluate EMORL on counselor reflection generation tasks, using text-scoring LLMs to evaluate the generations and provide rewards during RL fine-tuning. Through comprehensive experiments on the PAIR and Psych8k datasets, we demonstrate the advantages of EMORL against existing baselines: significantly lower and more stable training consumption ($17,529\\pm 1,650$ data points and $6,573\\pm 147.43$ seconds), improved scalability and explainability, and comparable performance across multiple objectives.","url_abs":"https://arxiv.org/abs/2505.02579v2","url_pdf":"https://arxiv.org/pdf/2505.02579v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"emorl-ensemble-multi-objective-reinforcement","repo_url":"https://github.com/engineerkong/emorl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multi-objective-reinforcement-learning","task_name":"Multi-Objective Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}