Cover Image

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Xianya, Ren, Feiyang, Chen, Xiang, Tian, Yu, Bi, Zhen, Yu, Haiyang, Huang, Sheng-Jun
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
by: Wan, Guancheng, et al.
Published: (2025)

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
by: Fan, Chongyu, et al.
Published: (2025)

EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models
by: Xing, Shangyu, et al.
Published: (2024)

Eight Methods to Evaluate Robust Unlearning in LLMs
by: Lynch, Aengus, et al.
Published: (2024)

Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting
by: Tan, Chenchen, et al.
Published: (2025)

Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts
by: Yu, Tian, et al.
Published: (2024)

SEPS: A Separability Measure for Robust Unlearning in LLMs
by: Jeung, Wonje, et al.
Published: (2025)

Shared Imagination: LLMs Hallucinate Alike
by: Zhou, Yilun, et al.
Published: (2024)

Mitigating Multimodal Hallucination via Phase-wise Self-reward
by: Zhang, Yu, et al.
Published: (2026)

Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
by: Zhao, Zhiyuan, et al.
Published: (2023)

Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
by: Qi, Siya, et al.
Published: (2026)

Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning
by: Liao, Yiming, et al.
Published: (2026)

HalluClean: A Unified Framework to Combat Hallucinations in LLMs
by: Zhao, Yaxin, et al.
Published: (2025)

The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure
by: Fan, Yu, et al.
Published: (2025)

Hierarchy-Aware Multimodal Unlearning for Medical AI
by: Wu, Fengli, et al.
Published: (2025)

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
by: Jang, Yeonwoo, et al.
Published: (2025)

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models
by: Liu, Zheyuan, et al.
Published: (2025)

Reducing Hallucinations in LLMs via Factuality-Aware Preference Learning
by: Chaduvula, Sindhuja, et al.
Published: (2026)

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
by: Chang, Kai-Po, et al.
Published: (2025)

FASTTRACK: Fast and Accurate Fact Tracing for LLMs
by: Chen, Si, et al.
Published: (2024)

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs
by: Cha, Sungmin, et al.
Published: (2024)

Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs
by: Fang, Yi, et al.
Published: (2024)

Representation-Aware Unlearning via Activation Signatures: From Suppression to Entity-Signature Erasure
by: Mahmood, Syed Naveed, et al.
Published: (2026)

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
by: Sun, Zhongxiang, et al.
Published: (2026)

Zeroth-Order Sharpness-Aware Learning with Exponential Tilting
by: Gong, Xuchen, et al.
Published: (2025)

Guardrail Baselines for Unlearning in LLMs
by: Thaker, Pratiksha, et al.
Published: (2024)

Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs
by: Yang, Yiheng, et al.
Published: (2025)

Explainable LLM Unlearning Through Reasoning
by: Liao, Junfeng, et al.
Published: (2026)

Enhancing Multi-hop Reasoning through Knowledge Erasure in Large Language Model Editing
by: Zhang, Mengqi, et al.
Published: (2024)

Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations
by: Sun, Yiyou, et al.
Published: (2025)

Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs
by: Phukan, Anirudh, et al.
Published: (2024)

Steering the Verifiability of Multimodal AI Hallucinations
by: Pang, Jianhong, et al.
Published: (2026)

Towards Robust Evaluation of Unlearning in LLMs via Data Transformations
by: Joshi, Abhinav, et al.
Published: (2024)

The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends
by: Zhang, Xinghua, et al.
Published: (2024)

Beyond Facts: Evaluating Intent Hallucination in Large Language Models
by: Hao, Yijie, et al.
Published: (2025)

Knowledge Verification to Nip Hallucination in the Bud
by: Wan, Fanqi, et al.
Published: (2024)

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
by: Patil, Vaidehi, et al.
Published: (2025)

Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling
by: Fang, Xinyue, et al.
Published: (2024)

Perception-Aware Policy Optimization for Multimodal Reasoning
by: Wang, Zhenhailong, et al.
Published: (2025)

Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
by: Zhang, Qinyan, et al.
Published: (2025)