Mitigating Self-Preference by Authorship Obfuscation

Taslim Mahbub; Shi Feng

AAAI 2026technical0 citations

Mitigating Self-Preference by Authorship Obfuscation

Abstract

Language models (LMs) judges are widely used to evaluate the quality of LM outputs. Despite many advantages, LM judges display concerning biases that can impair their integrity in evaluations. One such bias is self-preference: LM judges preferring their own answers over those produced by other LMs or humans. The bias is hard to eliminate as frontier LM judges can distinguish their own outputs from those of others, even when the evaluation candidates are not labeled with their sources. In this paper, we investigate strategies to mitigate self-preference by reducing the LM judges

BibTeX

@inproceedings{aaai2026_mitigatingselfpr,
  title = {Mitigating Self-Preference by Authorship Obfuscation},
  author = {Taslim Mahbub and Shi Feng},
  booktitle = {AAAI 2026},
  year = {2026}
}