FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models
cs.AI
Submitted: 2026-06-28
Updated: 2026-09-15
Comments: 18 pages, 5 figures, 27 tables. Corrected author list; Yichen Guo, Kai Tang, and Jinhao You contributed equally
Code: https://github.com/EasonAI-5589/LLaVA-Hallucination
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- PaLM-E: An Embodied Multimodal Language Model
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Hallucination of Multimodal Large Language Models: A Survey
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- The Llama 3 Herd of Models
- The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
- Mistral 7B
- A Survey on Hallucination in Large Vision-Language Models
- MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
- LLaMA: Open and Efficient Foundation Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- SimVLM: Simple Visual Language Model Pretraining with Weak Supervision
- Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
- PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning
- Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection