FairQE combines gender-cue detection, variant generation, and LLM-based reasoning in a multi-agent setup to reduce gender bias in machine translation quality estimation while preserving overall accuracy.
gender_ambiguous
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FairQE: Multi-Agent Framework for Mitigating Gender Bias in Translation Quality Estimation
FairQE combines gender-cue detection, variant generation, and LLM-based reasoning in a multi-agent setup to reduce gender bias in machine translation quality estimation while preserving overall accuracy.