CAS mitigates object hallucinations in MLLMs by extracting two context preference vectors from designed conflict samples and applying signed residual injection at mid-early MLP layers without retraining or added latency.
V-iti: Mitigating hallucinations in multimodal large language models via visual inference-time intervention
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LIME reduces hallucinations in multimodal LLMs by using LRP to boost perceptual modality contributions through inference-time KV updates.
citing papers explorer
-
Rethinking Visual Neglect: Steering via Context-Preference for MLLM Hallucination Mitigation
CAS mitigates object hallucinations in MLLMs by extracting two context preference vectors from designed conflict samples and applying signed residual injection at mid-early MLP layers without retraining or added latency.
-
Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time
LIME reduces hallucinations in multimodal LLMs by using LRP to boost perceptual modality contributions through inference-time KV updates.