Pith. sign in

B ias F ilter: An Inference-Time Debiasing Framework for Large Language Models

1 Pith paper cite this work, alongside 1 external citations. Polarity classification is still indexing.

1 Pith paper citing it
1 external citations · OpenAlex

fields

cs.CL 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

A Heuristic Perspective on Debiasing Language Models

cs.CL · 2026-08-01 · conditional · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • A Heuristic Perspective on Debiasing Language Models cs.CL · 2026-08-01 · conditional · none · ref 70

    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.