SIRA mitigates hallucinations in LVLMs by internally contrasting full visual access against a masked late-layer branch that retains shared context but lacks fine-grained visual evidence.
Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 5roles
baseline 1polarities
baseline 1representative citing papers
Omnimodal LLMs encode premise-perception mismatches in hidden states yet almost never reject false textual claims, exposing a representation-action gap that is modality-asymmetric and prompt-resistant.
OPPO is an evidence-aware preference optimization objective that contrasts faithful responses under varying visual evidence strengths to reduce hallucinations in MLLMs.
Layer-wise Laplacian energy of visual attention reveals hallucination emergence in MLLMs and enables LaSCD, a closed-form logit remapping strategy that mitigates hallucinations while preserving general performance.
LIME reduces hallucinations in multimodal LLMs by using LRP to boost perceptual modality contributions through inference-time KV updates.
citing papers explorer
-
Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
SIRA mitigates hallucinations in LVLMs by internally contrasting full visual access against a masked late-layer branch that retains shared context but lacks fine-grained visual evidence.
-
Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
Omnimodal LLMs encode premise-perception mismatches in hidden states yet almost never reject false textual claims, exposing a representation-action gap that is modality-asymmetric and prompt-resistant.
-
Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
OPPO is an evidence-aware preference optimization objective that contrasts faithful responses under varying visual evidence strengths to reduce hallucinations in MLLMs.
-
When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs
Layer-wise Laplacian energy of visual attention reveals hallucination emergence in MLLMs and enables LaSCD, a closed-form logit remapping strategy that mitigates hallucinations while preserving general performance.
-
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.