INTER is a training-free logit-correction method that adds Harsanyi interaction scores to selected keyword tokens, lowering hallucination on six LVLM benchmarks.
Technical Note: Game-Theoretic Interactions of Different Orders
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
In this study, we define interaction components of different orders between two input variables based on game theory. We further prove that interaction components of different orders satisfy several desirable properties.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
INTER is a training-free logit-correction method that adds Harsanyi interaction scores to selected keyword tokens, lowering hallucination on six LVLM benchmarks.