Review
JudgeBreak: Is Taste Hidden in the Layers? Stress-Testing Reward Models and LLM Judges with Representation-Based Subjective Evaluation
JudgeBreak, a benchmark of 95 evaluation settings spanning creative writing, summarization, safety, safety, 10 languages, and 33 writing genres, is introduced, showing that text quality is often more recoverable.
Vanya Bannihatti Kumar, Anish Narang, Mayand Anand et al.
· 1 citation