Pith. sign in

REVIEW 1 cited by

BiasDora: Exploring Hidden Biased Associations in Vision-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 2407.02066 v2 pith:5L7T2NE5 submitted 2024-07-02 cs.CL

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

Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime. This narrow scope often overlooks a vast range of unexamined implicit associations, restricting the identification and, hence, mitigation of such biases. We address this gap by probing VLMs to (1) uncover hidden, implicit associations across 9 bias dimensions. We systematically explore diverse input and output modalities and (2) demonstrate how biased associations vary in their negativity, toxicity, and extremity. Our work (3) identifies subtle and extreme biases that are typically not recognized by existing methodologies. We make the Dataset of retrieved associations, (Dora), publicly available here https://github.com/chahatraj/BiasDora.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Dual-character narrative prompts reveal gender biases in six multimodal LLMs that are largely invisible in single-character evaluations, and GENRES provides a structured benchmark to measure them.

Pith tools