Presents cue interventions and tie-aware metrics to detect rationalization bias in LLM judges and demonstrates that PROOF-BEFORE-PREFERENCE reduces cue anchoring compared to baselines.
Available: https://arxiv.org/abs/2508.19827
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges
Presents cue interventions and tie-aware metrics to detect rationalization bias in LLM judges and demonstrates that PROOF-BEFORE-PREFERENCE reduces cue anchoring compared to baselines.