technique
Personalized Evaluation as Learning
techniqueactiveprovisional
personalized-evaluation-as-learning-c345c6e4·1 events·first seen 16d agoAliases: Personalized Evaluation as Learning
Co-occurring entities
More like this (12)
Evaluation Cards: An Interpretive Layer for AI Evaluation ReportingPreference-Aware Rubric LearningMulti-Turn Evaluation of Deep Research Agents Under Process-Level FeedbackValueEvalSkill-RM: Unifying Heterogeneous Evaluation Criteria via Agent SkillEvaluation on the HubT-EvalCommunity EvalsLearning to Summarize with Human FeedbackClass-Incremental LearningContinual Learningpersonalized AI agents
Recent events (1)
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.