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.
In The 2023 Conference on Empirical Methods in Natural Lan- guage Processing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 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.