Skip to content
conftrace_

over-trust penalty

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

self-attention matrix (1) beam search decoding (1) hallucination mitigation (1) multimodal large language model (1)

Papers

OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation CVPR 2024