KV-cache compression

WoodPecker

Woodpecker: Hallucination Correction for Multimodal Large Language Models

Superseded baseline#233 of 234 most-superseded · first seen Oct 24, 2023

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites WoodPecker as a baseline.

WoodPecker~yin2024woodpecker introduces an additional visual model to monitor and ask the original model to regenerate hallucinated contents
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.