Entity · technique

Preference-Aware Rubric Learning

techniqueactivepreference-aware-rubric-learning-2d49e817·1 events·first seen Jun 1, 2026

Aliases: Preference-Aware Rubric Learning

Co-occurring entities

LLM-as-a-Judge PARL Reinforcement Learning Personalized Evaluation as Learning

More like this (12)

Rubric-based Feedback Evaluation rubric-based reward shaping Rubric Reward SERPO: Self-Evolving Rubric Policy Optimization for Open-Ended Test-Time Reinforcement Learning rubric-based rewards Rubrics on Trial Difference-Aware Retrieval Policies for Imitation Learning When Rubrics Change: Cross-Rubric Generalization for Critical Thinking Essay Scoring Role-Aware Policy Optimization Joint Rating Learning Reference-Augmented Training Personalized Evaluation as Learning

Recent events (1)

5arXiv · cs.CL·Jun 1, 2026·source ↗

PARL: Preference-Aware Rubric Learning for Personalized LLM Evaluation

This paper introduces PARL (Preference-Aware Rubric Learning), a framework that reframes personalized LLM evaluation as a learning problem rather than static judgment. PARL induces preference-aware evaluation rubrics from raw user interaction histories and uses a discriminative reinforcement learning objective to contrast user-authored responses against model outputs, capturing user-specific decision boundaries. Experiments on personalized text generation tasks show PARL produces high-fidelity rubrics that generalize across users and tasks, outperforming existing LLM-as-a-judge and automatic metric approaches.

Evaluation and Benchmarking Agent and Tool Ecosystem Preference-Aware Rubric Learning LLM-as-a-Judge PARL +3 more