Image de couverture de livre

Neutralizing Backdoors through Information Conflicts for Large Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Chen, Sun, Yuchen, Gong, Xueluan, Gao, Jiaxin, Lam, Kwok-Yan
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution
par: Chen, Chen, et autres
Publié: (2025)

Plato's Form: Toward Backdoor Defense-as-a-Service for LLMs with Prototype Representations
par: Chen, Chen, et autres
Publié: (2026)

The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents
par: Chen, Chen, et autres
Publié: (2026)

Hidden Data Privacy Breaches in Federated Learning
par: Gong, Xueluan, et autres
Publié: (2024)

Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems
par: Gao, Jiaxin, et autres
Publié: (2025)

AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions
par: Chen, Chen, et autres
Publié: (2024)

Detecting Stealthy Backdoor Samples based on Intra-class Distance for Large Language Models
par: Chen, Jinwen, et autres
Publié: (2025)

Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
par: Mo, Wenjie, et autres
Publié: (2023)

Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models
par: Liu, Yantao, et autres
Publié: (2024)

Attribution Techniques for Mitigating Hallucinated Information in RAG Systems: A Survey
par: Zhao, Yuqing, et autres
Publié: (2026)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
par: Xu, Jiashu, et autres
Publié: (2023)

ConInstruct: Evaluating Large Language Models on Conflict Detection and Resolution in Instructions
par: He, Xingwei, et autres
Publié: (2025)

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
par: Li, Haoran, et autres
Publié: (2024)

UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models
par: Xu, Xin, et autres
Publié: (2025)

Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating
par: Zhang, Binchi, et autres
Publié: (2025)

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
par: Yan, Jun, et autres
Publié: (2023)

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
par: Cao, Yuanpu, et autres
Publié: (2023)

Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models
par: Wu, Weiyi, et autres
Publié: (2025)

Resolving Knowledge Conflicts in Large Language Models
par: Wang, Yike, et autres
Publié: (2023)

Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge
par: Li, Jiahuan, et autres
Publié: (2024)

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models
par: Zhu, Tinghui, et autres
Publié: (2024)

CoSearchAgent: A Lightweight Collaborative Search Agent with Large Language Models
par: Gong, Peiyuan, et autres
Publié: (2024)

DynamicMind: A Tri-Mode Thinking System for Large Language Models
par: Li, Wei, et autres
Publié: (2025)

Taming Knowledge Conflicts in Language Models
par: Li, Gaotang, et autres
Publié: (2025)

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models
par: Wang, Fei, et autres
Publié: (2024)

Rethinking Backdoor Detection Evaluation for Language Models
par: Yan, Jun, et autres
Publié: (2024)

SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models
par: Gao, Xiang, et autres
Publié: (2024)

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
par: Wang, Zihan, et autres
Publié: (2025)

Mechanistic Exploration of Backdoored Large Language Model Attention Patterns
par: Baker, Mohammed Abu, et autres
Publié: (2025)

MEGen: Generative Backdoor into Large Language Models via Model Editing
par: Qiu, Jiyang, et autres
Publié: (2024)

A Novel Paradigm Boosting Translation Capabilities of Large Language Models
par: Guo, Jiaxin, et autres
Publié: (2024)

Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models
par: Lasnier, Théo, et autres
Publié: (2026)

Value-Action Alignment in Large Language Models under Privacy-Prosocial Conflict
par: Chen, Guanyu, et autres
Publié: (2026)

Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personas
par: Kwok, Louis, et autres
Publié: (2024)

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
par: Xie, Jian, et autres
Publié: (2023)

LTD-Bench: Evaluating Large Language Models by Letting Them Draw
par: Lin, Liuhao, et autres
Publié: (2025)

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
par: Yang, Jingyuan, et autres
Publié: (2025)

LLM4Ranking: An Easy-to-use Framework of Utilizing Large Language Models for Document Reranking
par: Liu, Qi, et autres
Publié: (2025)

Measuring Maximum Activations in Open Large Language Models
par: Chen, Luxuan, et autres
Publié: (2026)

Large Language Models for Healthcare Text Classification: A Systematic Review
par: Sakai, Hajar, et autres
Publié: (2025)