An automated framework using equal-quality response pairs quantifies self-preference bias in LLM judges and reduces it by 31.5% via a cognitive-load-based multi-dimensional evaluation strategy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Quantifying and Mitigating Self-Preference Bias of LLM Judges
An automated framework using equal-quality response pairs quantifies self-preference bias in LLM judges and reduces it by 31.5% via a cognitive-load-based multi-dimensional evaluation strategy.