Imagen de Portada

CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Min, Nay Myat, Pham, Long H., Li, Yige, Sun, Jun
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models
por: Min, Nay Myat, et al.
Publicado: (2026)

CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models
por: Min, Nay Myat, et al.
Publicado: (2026)

Propaganda AI: An Analysis of Semantic Divergence in Large Language Models
por: Min, Nay Myat, et al.
Publicado: (2025)

Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning
por: Min, Nay Myat, et al.
Publicado: (2024)

AutoBackdoor: Automating Backdoor Attacks via LLM Agents
por: Li, Yige, et al.
Publicado: (2025)

The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
por: Xiao, Quan, et al.
Publicado: (2025)

Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing
por: Li, Zhe, et al.
Publicado: (2025)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
por: Xu, Jiashu, et al.
Publicado: (2023)

ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training
por: Liang, Yu, et al.
Publicado: (2026)

Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs
por: Li, Yige, et al.
Publicado: (2026)

Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
por: Yang, Nakyeong, et al.
Publicado: (2023)

Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs
por: Zhao, Wei, et al.
Publicado: (2025)

Knowledge-based Consistency Testing of Large Language Models
por: Rajan, Sai Sathiesh, et al.
Publicado: (2024)

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation
por: Jin, Haoran, et al.
Publicado: (2025)

Leveraging Large Language Models for Suicide Detection on Social Media with Limited Labels
por: Nguyen, Vy, et al.
Publicado: (2024)

Bridging Internal Probability and Self-Consistency for Effective and Efficient LLM Reasoning
por: Zhou, Zhi, et al.
Publicado: (2025)

Stepwise Self-Consistent Mathematical Reasoning with Large Language Models
por: Zhao, Zilong, et al.
Publicado: (2024)

SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification
por: Jiao, Difan, et al.
Publicado: (2023)

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
por: Shu, Dong, et al.
Publicado: (2025)

Analyzing And Editing Inner Mechanisms Of Backdoored Language Models
por: Lamparth, Max, et al.
Publicado: (2023)

Automating Steering for Safe Multimodal Large Language Models
por: Wu, Lyucheng, et al.
Publicado: (2025)

Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
por: Chen, Weizhe, et al.
Publicado: (2024)

PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning
por: Zou, Jiaru, et al.
Publicado: (2024)

Induced Numerical Instability: Hidden Costs in Multimodal Large Language Models
por: Wong, Wai Tuck, et al.
Publicado: (2026)

Logically Consistent Language Models via Neuro-Symbolic Integration
por: Calanzone, Diego, et al.
Publicado: (2024)

Rethinking Entropy Regularization in Large Reasoning Models
por: Jiang, Yuxian, et al.
Publicado: (2025)

DReSS: Data-driven Regularized Structured Streamlining for Large Language Models
por: Feng, Mingkuan, et al.
Publicado: (2025)

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning
por: Chen, Yanda, et al.
Publicado: (2024)

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
por: Lin, Huawei, et al.
Publicado: (2025)

Pre-training Limited Memory Language Models with Internal and External Knowledge
por: Zhao, Linxi, et al.
Publicado: (2025)

Do Influence Functions Work on Large Language Models?
por: Li, Zhe, et al.
Publicado: (2024)

KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection
por: Li, Yuexin, et al.
Publicado: (2024)

Consistency Checks for Language Model Forecasters
por: Paleka, Daniel, et al.
Publicado: (2024)

FAS: Fast ANN-SNN Conversion for Spiking Large Language Models
por: Chen, Long, et al.
Publicado: (2025)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
por: Jiang, Peihai, et al.
Publicado: (2025)

Unveiling and Addressing Pseudo Forgetting in Large Language Models
por: Sun, Huashan, et al.
Publicado: (2024)

Benchmarking the Capabilities of Large Language Models in Transportation System Engineering: Accuracy, Consistency, and Reasoning Behaviors
por: Syed, Usman, et al.
Publicado: (2024)

Large Language Models as Computable Approximations to Solomonoff Induction
por: Wan, Jun, et al.
Publicado: (2025)

Beware of Calibration Data for Pruning Large Language Models
por: Ji, Yixin, et al.
Publicado: (2024)

Mastering Board Games by External and Internal Planning with Language Models
por: Schultz, John, et al.
Publicado: (2024)