DeCo is a model-agnostic decoding method that adaptively mixes earlier-layer representations to counteract language-prior suppression of visual evidence, reducing object hallucinations across Multimodal Large Language Models (MLLMs) with modest latency overhead.

Authors

• Person: Not available Organization: GitHub
  EdinburghNLP/awesome-hallucination-detection - GitHub

Sources

• EdinburghNLP/awesome-hallucination-detection - GitHub github.com GitHub via serper

Referenced by nodes (1)

• Multimodal Large Language Models concept