Preference Leakage: A Contamination Problem in LLM-as-a-judge
Paper
•
2502.01534
•
Published
•
40
LLM-as-a-judge
-
-
Great Models Think Alike and this Undermines AI Oversight
Paper • 2502.04313 • Published • 33 -
CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives
Paper • 2504.10823 • Published • 15 -
CLEAR: Error Analysis via LLM-as-a-Judge Made Easy
Paper • 2507.18392 • Published • 19 -
TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
Paper • 2509.21117 • Published • 29