Independent, non-fine-tuned judge models align most closely with human label-flip judgments, yet all automated judges fall well short of human evaluation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals
Independent, non-fine-tuned judge models align most closely with human label-flip judgments, yet all automated judges fall well short of human evaluation.