一作ACL 2026Workshop· ACL System Demonstrations
A uto C hecklist: Composable Pipelines for Checklist Generation and Scoring with LLM -as-a-Judge
Karen Zhou · Chenhao Tan
摘要
Checklists have emerged as a popular approach for interpretable and fine-grained evaluation, particularly with LLM-as-a-Judge. Beyond evaluation, these structured criteria can serve as signals for model alignment, reinforcement learning, and self-correction. To support these use cases, we present...