Copertina

Can Editing LLMs Inject Harm?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Canyu, Huang, Baixiang, Li, Zekun, Chen, Zhaorun, Lai, Shiyang, Xu, Xiongxiao, Gu, Jia-Chen, Gu, Jindong, Yao, Huaxiu, Xiao, Chaowei, Yan, Xifeng, Wang, William Yang, Torr, Philip, Song, Dawn, Shu, Kai
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Can Knowledge Editing Really Correct Hallucinations?
di: Huang, Baixiang, et al.
Pubblicazione: (2024)

Can Large Language Models Identify Authorship?
di: Huang, Baixiang, et al.
Pubblicazione: (2024)

Authorship Attribution in the Era of LLMs: Problems, Methodologies, and Challenges
di: Huang, Baixiang, et al.
Pubblicazione: (2024)

SST: Multi-Scale Hybrid Mamba-Transformer Experts for Time Series Forecasting
di: Xu, Xiongxiao, et al.
Pubblicazione: (2024)

MetaGAD: Meta Representation Adaptation for Few-Shot Graph Anomaly Detection
di: Xu, Xiongxiao, et al.
Pubblicazione: (2023)

Can Large Language Model Agents Simulate Human Trust Behavior?
di: Xie, Chengxing, et al.
Pubblicazione: (2024)

Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation
di: Wang, Haoran, et al.
Pubblicazione: (2025)

Can LLM-Generated Misinformation Be Detected?
di: Chen, Canyu, et al.
Pubblicazione: (2023)

Deep Research Brings Deeper Harm
di: Chen, Shuo, et al.
Pubblicazione: (2025)

Can Multimodal LLMs Perform Time Series Anomaly Detection?
di: Xu, Xiongxiao, et al.
Pubblicazione: (2025)

Can an Individual Manipulate the Collective Decisions of Multi-Agents?
di: Liu, Fengyuan, et al.
Pubblicazione: (2025)

Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?
di: Yu, Junchi, et al.
Pubblicazione: (2025)

Taxonomy-Guided Zero-Shot Recommendations with LLMs
di: Liang, Yueqing, et al.
Pubblicazione: (2024)

As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?
di: Hu, Anjun, et al.
Pubblicazione: (2024)

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
di: Chen, Zhaorun, et al.
Pubblicazione: (2024)

LLM Jailbreak Detection for (Almost) Free!
di: Chen, Guorui, et al.
Pubblicazione: (2025)

Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
di: Huang, Baixiang, et al.
Pubblicazione: (2025)

A Guardrail for Safety Preservation: When Safety-Sensitive Subspace Meets Harmful-Resistant Null-Space
di: Zhang, Bingjie, et al.
Pubblicazione: (2025)

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
di: Luo, Haochen, et al.
Pubblicazione: (2024)

Influencer Backdoor Attack on Semantic Segmentation
di: Lan, Haoheng, et al.
Pubblicazione: (2023)

Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?
di: Chen, Shuo, et al.
Pubblicazione: (2023)

Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models
di: Gao, Kuofeng, et al.
Pubblicazione: (2024)

Reimagining Safety Alignment with An Image
di: Xia, Yifan, et al.
Pubblicazione: (2025)

Latent Guard: a Safety Framework for Text-to-image Generation
di: Liu, Runtao, et al.
Pubblicazione: (2024)

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?
di: Chen, Canyu, et al.
Pubblicazione: (2024)

UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Language Models
di: Gu, Xiaojie, et al.
Pubblicazione: (2025)

PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs
di: Wu, Yixuan, et al.
Pubblicazione: (2025)

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
di: Li, Hang, et al.
Pubblicazione: (2023)

Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution
di: Liu, Fengyuan, et al.
Pubblicazione: (2024)

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
di: Gu, Jia-Chen, et al.
Pubblicazione: (2024)

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
di: Chen, Zhaorun, et al.
Pubblicazione: (2024)

TraceDet: Hallucination Detection from the Decoding Trace of Diffusion Large Language Models
di: Chang, Shenxu, et al.
Pubblicazione: (2025)

Improving Adversarial Transferability via Model Alignment
di: Ma, Avery, et al.
Pubblicazione: (2023)

Towards Effective Model Editing for LLM Personalization
di: Huang, Baixiang, et al.
Pubblicazione: (2025)

Multimodal Pragmatic Jailbreak on Text-to-image Models
di: Liu, Tong, et al.
Pubblicazione: (2024)

A Survey on Responsible Generative AI: What to Generate and What Not
di: Gu, Jindong
Pubblicazione: (2024)

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
di: Gao, Kuofeng, et al.
Pubblicazione: (2024)

Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples
di: Gao, Kuofeng, et al.
Pubblicazione: (2024)

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models
di: Xing, Songlong, et al.
Pubblicazione: (2026)

Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters
di: Potter, Yujin, et al.
Pubblicazione: (2024)