Imagen de Portada

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ding, Peng, Kuang, Jun, Wang, Zongyu, Cao, Xuezhi, Cai, Xunliang, Chen, Jiajun, Huang, Shujian
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Friend or Foe: How LLMs' Safety Mind Gets Fooled by Intent Shift Attack
por: Ding, Peng, et al.
Publicado: (2025)

Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
por: Ding, Peng, et al.
Publicado: (2024)

A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
por: Ding, Peng, et al.
Publicado: (2023)

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability
por: wang, Jiaming, et al.
Publicado: (2025)

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
por: Ding, Peng, et al.
Publicado: (2025)

LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
por: Nie, Dujun, et al.
Publicado: (2026)

LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation
por: Wang, Keheng, et al.
Publicado: (2024)

BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation
por: Du, Dayou, et al.
Publicado: (2024)

Making Mathematical Reasoning Adaptive
por: Lai, Zhejian, et al.
Publicado: (2025)

Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
por: Lin, Kaiqing, et al.
Publicado: (2025)

LLMs Know When They Know, but Do Not Act on It: A Metacognitive Harness for Test-time Scaling
por: Cao, Qi, et al.
Publicado: (2026)

EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs
por: Yeom, Jewon, et al.
Publicado: (2026)

MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models
por: Yan, Siyu, et al.
Publicado: (2025)

Forget What You Know about LLMs Evaluations -- LLMs are Like a Chameleon
por: Cohen-Inger, Nurit, et al.
Publicado: (2025)

Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
por: Luo, Wen, et al.
Publicado: (2026)

Why Don't You Know? Evaluating the Impact of Uncertainty Sources on Uncertainty Quantification in LLMs
por: Goloburda, Maiya, et al.
Publicado: (2026)

Why Knowing What To Do Is Not Enough
por: Keizer, Anne-Greet, et al.
Publicado: (2020)

SnapKV: LLM Knows What You are Looking for Before Generation
por: Li, Yuhong, et al.
Publicado: (2024)

The National Literacy Act: What Librarians Should Know.
por: Humes, Barbara
Publicado: (1994)

How and Why Libraries Are Changing: What We Know and What We Need To Know.
por: Troll, Denise A.
Publicado: (2002)

Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge
por: Li, Jiahuan, et al.
Publicado: (2024)

What You Don't Know Can Hurt You: How Well do Latent Safety Filters Understand Partially Observable Safety Constraints?
por: Kim, Matthew, et al.
Publicado: (2025)

Visually Dehallucinative Instruction Generation: Know What You Don't Know
por: Cha, Sungguk, et al.
Publicado: (2024)

Do You Know What Your Mission Is?
por: Balas, Janet L.
Publicado: (2007)

Knowing What LLMs DO NOT Know: A Simple Yet Effective Self-Detection Method
por: Zhao, Yukun, et al.
Publicado: (2023)

Extend Adversarial Policy Against Neural Machine Translation via Unknown Token
por: Zou, Wei, et al.
Publicado: (2025)

Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning
por: Zhao, Qiannian, et al.
Publicado: (2026)

Know What You Don't Know: Uncertainty Calibration of Process Reward Models
por: Park, Young-Jin, et al.
Publicado: (2025)

Know What You Don't Know: Selective Prediction for Early Exit DNNs
por: Bajpai, Divya Jyoti, et al.
Publicado: (2025)

Length Desensitization in Direct Preference Optimization
por: Liu, Wei, et al.
Publicado: (2024)

Do You Know What I Mean? A Syntactic Representation for Differential Bounded Awareness
por: Guerdjikova, Ani, et al.
Publicado: (2025)

What You Shouldn't Know About Quantum Computers
por: Ferrie, Chris
Publicado: (2024)

Open Access: What You Need to Know Now
por: Crawford, Walt
Publicado: (2011)

Getting Ready for RDA: What You Need to Know
por: Hart, Amy
Publicado: (2010)

What Every Librarian Should Know about the Americans with Disabilities Act.
por: Gunde, Michael G.
Publicado: (1991)

CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks
por: Fu, Lingyue, et al.
Publicado: (2025)

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs
por: Fan, Siqi, et al.
Publicado: (2025)

CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications
por: Joshi, Raviraj, et al.
Publicado: (2025)

AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
por: Jiayang, Cheng, et al.
Publicado: (2026)

Why Generate When You Can Transform? Unleashing Generative Attention for Dynamic Recommendation
por: Liu, Yuli, et al.
Publicado: (2025)