HEIMAT debiases language models by generating heuristic prompts, building substitution sets, and fine-tuning the model with a Jensen-Shannon divergence loss to align predictions across demographic groups, with no fixed preference datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Heuristic Perspective on Debiasing Language Models
HEIMAT debiases language models by generating heuristic prompts, building substitution sets, and fine-tuning the model with a Jensen-Shannon divergence loss to align predictions across demographic groups, with no fixed preference datasets.