Evidence-Calibrated Selective Decoding for Reliable Visual Question Answering
Visual question answering systems can produce confident responses that are weakly supported by their input images. Contrastive decoding can reduce this dependence on language priors, but a fixed correction may also overturn a correct answer, while selective answering can conceal errors by reducing…
By Shiyu Gu, Luis Miguel Santana, Rafael Enrique CruzarXiv - cs.CV (CV)
Read the full story
Originally published by arXiv - cs.CV (CV) on Nov 17, 2026.
Comments
Sign in to join the discussion.