Pith. sign in

REVIEW 2 cited by

FineDeb: A Debiasing Framework for Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.02453 v1 pith:YHDDZ2BP submitted 2023-02-05 cs.CL cs.CY

classification cs.CLcs.CY
keywords languagemodelsdebiasingfinedebframeworkmodelattentionbias
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As language models are increasingly included in human-facing machine learning tools, bias against demographic subgroups has gained attention. We propose FineDeb, a two-phase debiasing framework for language models that starts with contextual debiasing of embeddings learned by pretrained language models. The model is then fine-tuned on a language modeling objective. Our results show that FineDeb offers stronger debiasing in comparison to other methods which often result in models as biased as the original language model. Our framework is generalizable for demographics with multiple classes, and we demonstrate its effectiveness through extensive experiments and comparisons with state of the art techniques. We release our code and data on GitHub.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models

    cs.CL 2025-07 conditional novelty 6.0 of 10

    A new Chinese bias benchmark with 4,077 instances and five tasks indicates larger language models are less biased than smaller ones when bias is measured through understanding tasks.

  2. KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models

    cs.CL 2025-07 reject novelty 5.0 of 10

    An attention-alignment fine-tuning objective (KL, CE, and triplet losses) reduces some bias scores on BBQ and BOLD for Llama-3.2-3B, but not consistently across models and with notable accuracy drops.

Pith tools