Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers
Mixed-modality retrievers favor text over images; Trident reduces that bias.
2 stories, newest first · one card per story
Mixed-modality retrievers favor text over images; Trident reduces that bias.
Tri-PvP is a new benchmark revealing robust modality bias in omni-modal LLMs, with vision favoring perceptual signals and audio favoring propositional ones.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views