Entity · model

PARL

modelactiveparl-372f1daf·1 events·first seen Jun 1, 2026

Aliases: PARL

Co-occurring entities

Preference-Aware Rubric Learning LLM-as-a-Judge Reinforcement Learning Personalized Evaluation as Learning

More like this (12)

PARM PACE European Parliament PACT PLAID Bundestag SPEAR PEARL PaLI page-agent PDDL PALS

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