A fairness score built from token-level attribution and pruned multi-round dialogues links LLaVA models' reliance on sensitive image regions to demographic accuracy gaps.
Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rogriguez, and Krishna P Gummadi
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Interpreting Social Bias in LVLMs via Information Flow Analysis and Multi-Round Dialogue Evaluation
A fairness score built from token-level attribution and pruned multi-round dialogues links LLaVA models' reliance on sensitive image regions to demographic accuracy gaps.