MiCRo is a two‑stage framework that improves personalized preference learning for large language models. It first uses a context‑aware mixture model to capture diverse human preferences from large binary preference datasets, then applies an online routing strategy to dynamically adjust mixture weights based on context, reducing ambiguity. Experiments on multiple datasets show that MiCRo captures diverse preferences and enhances downstream personalization.
By Jingyan Shen, Jiarui Yao, Rui Yang, Yifan Sun, Feng Luo, Rui Pan, Tong Zhang, Han Zhao
arXiv:2608. 06400v1 Announce Type: new Abstract: Reward models are central to learning from human preferences, yet identifying what drives their predictions remains challenging.
By Yifan Wang, Jinyi Mu, Mayank Jobanputra, Yu Wang, Soyoung Oh, Isabel Valera, Vera Demberg
COPE (Continual Optimization with Personalized embedding and self-Evaluation) is a new framework that continually personalizes large language models using learnable user embeddings and self‑evaluation to generate proxy rewards. It integrates preference capture, self‑evaluation calibration, and personalized response optimization into a single update step, allowing continuous model updates even when explicit user feedback is sparse. Experiments demonstrate that COPE outperforms both training‑free and training‑based baselines, remains complementary to Retrieval‑Augmented Prompting, and shows reliable self‑evaluation, meaningful preference patterns, stable general capabilities, and robustness to shifting preferences and alternative evaluators.
By Ruike Cao, Fugen Yao, Liang Dong, Jian Xu, Guanjun Jiang, Li Xiao
arXiv:2606. 06178v1 Announce Type: new Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense.
By Jiahao Zeng, Ming Tang, Ningning Ding
arXiv:2510. 05342v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models.
By Hyung Gyu Rho
arXiv:2509. 22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks.
By Yaswanth Chittepu, Prasann Singhal, Greg Durrett, Scott Niekum
The paper introduces Personalized Group Relative Policy Optimization (P‑GRPO), a new alignment framework for large language models that separates advantage estimation from immediate batch statistics. By normalizing advantages using preference‑group‑specific reward histories instead of the concurrent generation group, P‑GRPO maintains contrastive signals for distinct user preferences. Experiments across various tasks show that P‑GRPO converges faster and yields higher rewards than standard GRPO, improving alignment with heterogeneous human preferences while preserving general capabilities.
By Jialu Wang, Heinrich Peters, Asad A. Butt, Navid Hashemi, Alireza Hashemi, Pouya M. Ghari, Joseph Hoover, James Rae, Morteza Dehghani
The paper introduces PLUS, a framework that uses reinforcement learning to generate text-based summaries of individual users’ preferences, characteristics, and past conversations. These summaries condition a reward model, allowing it to predict personalized response preferences and improving reward accuracy by 11–77 % over the standard Bradley‑Terry model. PLUS demonstrates robust performance with new users and topics, achieves a 25 % improvement over existing personalized RLHF techniques, and enables zero‑shot personalization for state‑of‑the‑art models like GPT‑4.
By Hyunji Nam, Yanming Wan, Mickel Liu, Peter Ahnn, Jianxun Lian, Natasha Jaques
arXiv:2608. 08604v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL) is a powerful framework for solving complex collaborative tasks, but it relies heavily on well-defined global reward functions.
By Ni Mu, Yao Luan, Yiqin Yang, Qing-Shan Jia
arXiv:2506. 13702v4 Announce Type: replace-cross Abstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by directly leveraging scalar feedback.
By Bilal Faye, Hanane Azzag, Mustapha Lebbah
arXiv:2605.16339v2 Announce Type: replace
Abstract: Preference learning in large language models relies on reward models as proxies for human judgment. However, these models frequently exhibit prefer...
By Shunchang Liu, Xin Chen, Belen Martin Urcelay, Francesco Croce
The paper introduces CurriPO, a tree‑structured curriculum that adapts to diverse user reward models in AI alignment. By automatically building a curriculum that branches and reuses reward models, it addresses the problem of users whose reward models are hard to optimize, a group often underserved by conventional methods. Experiments on personalized continuous control demonstrate that CurriPO improves population satisfaction by 1.2–2.1× over the best baseline while cutting training time.