Overthinking Causes Hallucination: Tracing Confounder Propagation in Vision Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | Shoby, Abin, Huy, Ta Duc, Nguyen, Tuan Dung, Ho, Minh Khoi, Chen, Qi, Hengel, Anton van den, Nguyen, Phi Le, Verjans, Johan W., Phan, Vu Minh Hieu |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
by: Nguyen, Tuan Dung, et al.
Published: (2026)
by: Nguyen, Tuan Dung, et al.
Published: (2026)
Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs
by: Nguyen, Dung, et al.
Published: (2025)
by: Nguyen, Dung, et al.
Published: (2025)
Interactive Medical Image Analysis with Concept-based Similarity Reasoning
by: Huy, Ta Duc, et al.
Published: (2025)
by: Huy, Ta Duc, et al.
Published: (2025)
Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
by: Huy, Ta Duc, et al.
Published: (2025)
by: Huy, Ta Duc, et al.
Published: (2025)
Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
by: Chowdhury, Townim Faisal, et al.
Published: (2025)
by: Chowdhury, Townim Faisal, et al.
Published: (2025)
AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis
by: Chowdhury, Townim F., et al.
Published: (2024)
by: Chowdhury, Townim F., et al.
Published: (2024)
Optimizing Electric Vehicle Charging Station Placement Using Reinforcement Learning and Agent-Based Simulations
by: Nguyen, Minh-Duc, et al.
Published: (2025)
by: Nguyen, Minh-Duc, et al.
Published: (2025)
CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation
by: Chowdhury, Townim Faisal, et al.
Published: (2024)
by: Chowdhury, Townim Faisal, et al.
Published: (2024)
Med-StepBench: A Hierarchical Reasoning Framework for Evaluating Hallucinations in Medical Vision-Language Models
by: Nguyen, Minh Khoi, et al.
Published: (2026)
by: Nguyen, Minh Khoi, et al.
Published: (2026)
On the maximum purity of absolutely separable bipartite states
by: Dung, Hoang Phi, et al.
Published: (2025)
by: Dung, Hoang Phi, et al.
Published: (2025)
A Survey of Medical Vision-and-Language Applications and Their Techniques
by: Chen, Qi, et al.
Published: (2024)
by: Chen, Qi, et al.
Published: (2024)
Eco‐Friendly Synthesis of Zinc Oxide and Magnesium Oxide Nanoparticles: Comparative Insights into Characterization, Electrochemical, and Photocatalytic Properties
by: Nguyen Duc Huy, et al.
Published: (2026)
by: Nguyen Duc Huy, et al.
Published: (2026)
TwinMixing: A Shuffle-Aware Feature Interaction Model for Multi-Task Segmentation
by: Do, Minh-Khoi, et al.
Published: (2026)
by: Do, Minh-Khoi, et al.
Published: (2026)
Learning to Stop Overthinking at Test Time
by: Bao, Hieu Tran, et al.
Published: (2025)
by: Bao, Hieu Tran, et al.
Published: (2025)
Fourier-Attentive Representation Learning: A Fourier-Guided Framework for Few-Shot Generalization in Vision-Language Models
by: Pham, Hieu Dinh Trung, et al.
Published: (2025)
by: Pham, Hieu Dinh Trung, et al.
Published: (2025)
Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph
by: Duc, Nguyen Minh, et al.
Published: (2026)
by: Duc, Nguyen Minh, et al.
Published: (2026)
A Framework for Controllable Multi-objective Learning with Annealed Stein Variational Hypernetworks
by: Nguyen, Minh-Duc, et al.
Published: (2025)
by: Nguyen, Minh-Duc, et al.
Published: (2025)
SoftCTRL: Soft conservative KL-control of Transformer Reinforcement Learning for Autonomous Driving
by: Huynh, Minh Tri, et al.
Published: (2024)
by: Huynh, Minh Tri, et al.
Published: (2024)
Dual Strategies for Test-Time Adaptation
by: Phuong, Nam Nguyen, et al.
Published: (2026)
by: Phuong, Nam Nguyen, et al.
Published: (2026)
Robust Aggregation for Federated Sequential Recommendation with Sparse and Poisoned Data
by: Nguyen, Minh Hieu
Published: (2026)
by: Nguyen, Minh Hieu
Published: (2026)
Enhanced Multimodal Video Retrieval System: Integrating Query Expansion and Cross-modal Temporal Event Retrieval
by: Vo, Van-Thinh, et al.
Published: (2025)
by: Vo, Van-Thinh, et al.
Published: (2025)
On asymptotic periodic solutions of fractional differential equations and applications
by: Luong, Vu Trong, et al.
Published: (2023)
by: Luong, Vu Trong, et al.
Published: (2023)
KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection
by: La, Tuan-Vinh, et al.
Published: (2025)
by: La, Tuan-Vinh, et al.
Published: (2025)
Existence of bounded asymptotic solutions of autonomous differential equations
by: Luong, Vu Trong, et al.
Published: (2024)
by: Luong, Vu Trong, et al.
Published: (2024)
On the separation Łojasiewicz exponents of real analytic sets in the real plane
by: Hoang, Phi Dung, et al.
Published: (2026)
by: Hoang, Phi Dung, et al.
Published: (2026)
Metacognitive Sensitivity for Test-Time Dynamic Model Selection
by: Trinh, Le Tuan Minh, et al.
Published: (2025)
by: Trinh, Le Tuan Minh, et al.
Published: (2025)
ViMQ: A Vietnamese Medical Question Dataset for Healthcare Dialogue System Development
by: Huy, Ta Duc, et al.
Published: (2023)
by: Huy, Ta Duc, et al.
Published: (2023)
Improving the Robustness of 3D Human Pose Estimation: A Benchmark and Learning from Noisy Input
by: Hoang, Trung-Hieu, et al.
Published: (2023)
by: Hoang, Trung-Hieu, et al.
Published: (2023)
Matrix-Scaled Consensus over Undirected Networks
by: Trinh, Minh Hoang, et al.
Published: (2023)
by: Trinh, Minh Hoang, et al.
Published: (2023)
Exploiting LLMs' Reasoning Capability to Infer Implicit Concepts in Legal Information Retrieval
by: Nguyen, Hai-Long, et al.
Published: (2024)
by: Nguyen, Hai-Long, et al.
Published: (2024)
"True" self-avoiding walks on general trees
by: Nguyen, Tuan-Minh
Published: (2026)
by: Nguyen, Tuan-Minh
Published: (2026)
Link prediction Graph Neural Networks for structure recognition of Handwritten Mathematical Expressions
by: Nguyen, Cuong Tuan, et al.
Published: (2025)
by: Nguyen, Cuong Tuan, et al.
Published: (2025)
Exploring the potential of AI in nurturing learner empathy, prosocial values and environmental stewardship
by: Lim, Kenneth Y T, et al.
Published: (2024)
by: Lim, Kenneth Y T, et al.
Published: (2024)
Semi-supervised 3D Semantic Scene Completion with 2D Vision Foundation Model Guidance
by: Pham, Duc-Hai, et al.
Published: (2024)
by: Pham, Duc-Hai, et al.
Published: (2024)
AgriKD: Cross-Architecture Knowledge Distillation for Efficient Leaf Disease Classification
by: Le, Minh-Dung, et al.
Published: (2026)
by: Le, Minh-Dung, et al.
Published: (2026)
A generation theorem for the perturbation of strongly continuous semigroups by unbounded operators
by: Bui, Xuan-Quang, et al.
Published: (2024)
by: Bui, Xuan-Quang, et al.
Published: (2024)
Asymptotic periodic solutions of differential equations with infinite delay
by: Huy, Nguyen Duc, et al.
Published: (2023)
by: Huy, Nguyen Duc, et al.
Published: (2023)
VNJPTranslate: A comprehensive pipeline for Vietnamese-Japanese translation
by: Phan, Hoang Hai, et al.
Published: (2025)
by: Phan, Hoang Hai, et al.
Published: (2025)
Dieu khien he da tac tu
by: Trinh, Minh Hoang, et al.
Published: (2026)
by: Trinh, Minh Hoang, et al.
Published: (2026)
Investigating Recent Large Language Models for Vietnamese Machine Reading Comprehension
by: Nguyen, Anh Duc, et al.
Published: (2025)
by: Nguyen, Anh Duc, et al.
Published: (2025)
Similar Items
-
Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations
by: Nguyen, Tuan Dung, et al.
Published: (2026) -
Localizing Before Answering: A Hallucination Evaluation Benchmark for Grounded Medical Multimodal LLMs
by: Nguyen, Dung, et al.
Published: (2025) -
Interactive Medical Image Analysis with Concept-based Similarity Reasoning
by: Huy, Ta Duc, et al.
Published: (2025) -
Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding
by: Huy, Ta Duc, et al.
Published: (2025) -
Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
by: Chowdhury, Townim Faisal, et al.
Published: (2025)