RL post-training on hallucination-forced multimodal data improves reasoning performance and can outperform standard training.
hub
Look twice before you answer: Memory-space visual retracing for hallucination mitiga- tion in multimodal large language models
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
LVLMs show vocabulary hijacking by inert tokens that decode to hijacking anchors; HABI locates them, NHAR finds resilient heads, and HAVAE boosts those heads to cut hallucinations.
LIME reduces hallucinations in multimodal LLMs by using LRP to boost perceptual modality contributions through inference-time KV updates.
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
Decoder-side Temporal Rebalancing (DTR) reduces hallucinations in Video-LLMs by mitigating over-dominance of a single anchor frame during inference without training or auxiliary models.
STEAR reduces spatial and temporal hallucinations in Video-LLMs via layer-aware evidence intervention from middle decoder layers in a single-encode pass.
Activation Replay boosts multimodal reasoning in post-trained LMMs by replaying low-entropy activations from base models to RLVR counterparts at test time via visual token manipulation.
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
citing papers explorer
-
Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models
RL post-training on hallucination-forced multimodal data improves reasoning performance and can outperform standard training.
-
Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space
DMLR performs dynamic visual-textual interleaving in latent space using confidence-guided latent policy gradient optimization and a dynamic visual injection strategy, yielding improved multimodal reasoning on benchmarks.
-
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
LVLMs show vocabulary hijacking by inert tokens that decode to hijacking anchors; HABI locates them, NHAR finds resilient heads, and HAVAE boosts those heads to cut hallucinations.
-
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.
-
Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs
PVM adds a parallel branch to LVLMs that directly supplies visual embeddings to prevent attention decay over long generated sequences, yielding accuracy gains on reasoning tasks with minimal overhead.
-
HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering
HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.
-
Relaxing Anchor-Frame Dominance for Mitigating Hallucinations in Video Large Language Models
Decoder-side Temporal Rebalancing (DTR) reduces hallucinations in Video-LLMs by mitigating over-dominance of a single anchor frame during inference without training or auxiliary models.
-
STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models
STEAR reduces spatial and temporal hallucinations in Video-LLMs via layer-aware evidence intervention from middle decoder layers in a single-encode pass.
-
Boosting Reasoning in Large Multimodal Models via Activation Replay
Activation Replay boosts multimodal reasoning in post-trained LMMs by replaying low-entropy activations from base models to RLVR counterparts at test time via visual token manipulation.
-
Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
- Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models