#preference learning

try —

9 papers match

cs.LG2026

AutoPref: Automatic Discovery of Task-Specific Preference Objectives for Neural Combinatorial Optimization

Shengda Gu, Kai Li, Xinyi Ke +3

AutoPref uses a large language model to automatically discover and compose pairwise loss and weighting programs that define preference objectives for neural combinatorial optimizat…

#neural combinatorial optimization#preference learning#reinforcement learning#automated objective discovery
cs.CL2026

Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence

Haocheng Yang, Licheng Pan, Xiaoxi Li +5

The paper proposes a query‑only method that automatically creates and validates fine‑grained rubrics for evaluating large language models by using synthetic rubric‑conditioned resp…

#rubric generation#large language model evaluation#synthetic pairwise data#preference learning
cs.CV2026

Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs

Zhixiao Zheng, Zheren Fu, Zhiyuan Yao +3

The paper introduces Groc-PO, a preference‑optimization framework that provides stage‑specific supervision for object grounding, contextual grounding, and grounded reasoning in mul…

#multimodal llms#preference learning#grounded reasoning#visual hallucination mitigation
cs.LG2026

RENEW: Towards Learning World Models and Repairing Model Exploitation from Preferences

Logan Mondal Bhamidipaty, Mykel Kochenderfer, Subramanian Ramamoorthy

The paper introduces RENEW, a method that uses human preferences over imagined rollouts to correct model exploitation in offline model-based reinforcement learning, focusing fine‑t…

#world models#offline reinforcement learning#human feedback#model exploitation
cs.RO2026

Deployable Human Preference Alignment in Robotics: Learning Representative Rewards from Diverse Human Preferences

Taehyung Kim, Gwangmo Lee, Minjun Chang +2

The paper proposes Preference-based REward Clustering (PREC), a method that groups users with similar preferences and learns a compact set of reward models from binary feedback to…

#human-robot interaction#preference learning#reward modeling#policy clustering
cs.AI2026

Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models

Ilias Kazantzidis, Timothy J. Norman, Yali Du +1

The paper introduces DROPJ, a human‑in‑the‑loop approach that uses preferences and justifications collected from users interacting with a learned world model to train a reward mode…

#safe reinforcement learning#human feedback#preference learning#world models
cs.CL2026

Meta-Learning Preferences for Multilingual LLM Alignment

Jiaying Lin, Seongho Son, Nam Phuong Tran +3

The paper introduces a meta-learning method that uses preference data from high-resource languages to quickly adapt large language models to low-resource languages with very few hu…

#multilingual alignment#meta-learning#preference learning#reinforcement learning from human feedback
cs.LG2026

Generalizing Preference-based Reinforcement Learning: a Rationality Model for Incomparability

Simone Drago, Marco Mussi, Leonardo Bianconi +1

The paper extends preference‑based reinforcement learning by allowing human experts to label trajectory pairs as incomparable, and introduces a Bradley‑Terry‑inspired rationality m…

#preference learning#incomparability#multi‑objective reward modeling#sample complexity
cs.RO2026

Freeform Preference Learning for Robotic Manipulation

Marcel Torne, Anubha Mahajan, Abhijnya Bhat +1

The paper introduces Freeform Preference Learning, a method that lets humans give natural-language preference criteria for robot trajectories, enabling robots to learn multi-dimens…

#preference learning#robotic manipulation#reward modeling#human-in-the-loop

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.