Pith. sign in

A prompt array keeps the bias away: Debiasing vision-language models with ad- versarial learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

FairReason: Balancing Reasoning and Social Bias in MLLMs

cs.AI · 2025-07-30 · conditional · novelty 5.0

A 1:4 debias-to-reasoning training mix under GRPO reinforcement learning yields the best bias-reasoning trade-off in small MLLMs, cutting measured stereotype scores by about 10% while retaining about 88% of reasoning accuracy.

citing papers explorer

Showing 1 of 1 citing paper.

  • FairReason: Balancing Reasoning and Social Bias in MLLMs cs.AI · 2025-07-30 · conditional · none · ref 3

    A 1:4 debias-to-reasoning training mix under GRPO reinforcement learning yields the best bias-reasoning trade-off in small MLLMs, cutting measured stereotype scores by about 10% while retaining about 88% of reasoning accuracy.