Glossary

Searchable terminology from accessibility, web standards, and related fields.

2 results found in multimodal AI.

Contrastive Decoding (Visual Contrastive Decoding, VCD)
Contrastive decoding is a technique for reducing hallucinations in large language model and multimodal AI outputs by comparing token probability distributions across different input conditions. The co…
Visual Hallucination (AI hallucination, MLLM hallucination)
In the context of multimodal AI systems, visual hallucination refers to the generation of descriptions or responses that contain information not grounded in the actual visual input—fabricating non-exi…