Cover Image

Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Jinrui, Wu, Zhangtai, Wu, Zhen, Dai, Xinyu
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mitigating Modal Imbalance in Multimodal Reasoning
by: Wu, Chen Henry, et al.
Published: (2025)

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification
by: Sun, Han, et al.
Published: (2026)

Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers
by: Nam, Andrew, et al.
Published: (2025)

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs
by: Zhang, Xiaofeng, et al.
Published: (2024)

Causal-HalBench: Uncovering LVLMs Object Hallucinations Through Causal Intervention
by: Xu, Zhe, et al.
Published: (2025)

Persona-Aware Alignment Framework for Personalized Dialogue Generation
by: Li, Guanrong, et al.
Published: (2025)

Counterfactual Language Reasoning for Explainable Recommendation Systems
by: Li, Guanrong, et al.
Published: (2025)

Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
by: Li, Jiaming, et al.
Published: (2025)

Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules
by: Jiang, Yanbei, et al.
Published: (2025)

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models
by: Ho, Zheng Yi, et al.
Published: (2024)

Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems
by: Zhu, Junze, et al.
Published: (2026)

A Conflict-Aware Penalty and Statistical Loss Framework for Balancing Modalities and Enhancing Stability in Multimodal Sentiment Analysis
by: Dai, Jianheng, et al.
Published: (2026)

DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers
by: Zhang, Hanling, et al.
Published: (2025)

Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis
by: Cai, Wang, et al.
Published: (2026)

Modality Selection and Skill Segmentation via Cross-Modality Attention
by: Jiang, Jiawei, et al.
Published: (2025)

Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs
by: Yu, Liu, et al.
Published: (2025)

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination
by: Liang, Qiyao, et al.
Published: (2026)

Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs
by: Wang, Wei-Yao, et al.
Published: (2025)

Hallucination as Trajectory Commitment: Causal Evidence for Asymmetric Attractor Dynamics in Transformer Generation
by: Akarlar, G. Aytug
Published: (2026)

Rethinking Relation Extraction: Beyond Shortcuts to Generalization with a Debiased Benchmark
by: He, Liang, et al.
Published: (2025)

HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Models
by: Jiang, Xinyan, et al.
Published: (2025)

HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads
by: Wang, Juyuan, et al.
Published: (2026)

Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models
by: Hu, Xinmiao, et al.
Published: (2025)

MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models
by: Chung, Sangyun, et al.
Published: (2026)

Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models
by: Jin, Zhuoran, et al.
Published: (2024)

Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads
by: Wu, Jinman, et al.
Published: (2026)

Reallocating Attention Across Layers to Reduce Multimodal Hallucination
by: Lu, Haolang, et al.
Published: (2025)

A Head to Predict and a Head to Question: Pre-trained Uncertainty Quantification Heads for Hallucination Detection in LLM Outputs
by: Shelmanov, Artem, et al.
Published: (2025)

Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution
by: Binkyte, Ruta, et al.
Published: (2026)

Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models
by: Liu, Qiang, et al.
Published: (2025)

Hallucination Detection and Hallucination Mitigation: An Investigation
by: Luo, Junliang, et al.
Published: (2024)

Causality Enhancement for Cross-Domain Recommendation
by: Wu, Zhibo, et al.
Published: (2025)

WebNavigator: Global Web Navigation via Interaction Graph Retrieval
by: Zhang, Xuanwang, et al.
Published: (2026)

Dynamic Demonstrations Controller for In-Context Learning
by: Zhao, Fei, et al.
Published: (2023)

LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer
by: Wang, Jiing-Ping, et al.
Published: (2024)

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs
by: Guo, Peizheng, et al.
Published: (2025)

Early GVHD Prediction in Liver Transplantation via Multi-Modal Deep Learning on Imbalanced EHR Data
by: Jiang, Yushan, et al.
Published: (2025)

Retrieval-Augmented Generation with Conflicting Evidence
by: Wang, Han, et al.
Published: (2025)

ECon: On the Detection and Resolution of Evidence Conflicts
by: Jiayang, Cheng, et al.
Published: (2024)

DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations
by: Gema, Aryo Pradipta, et al.
Published: (2024)