Copertina

$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kang, Mintong, Li, Bo
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
di: Kang, Mintong, et al.
Pubblicazione: (2024)

AudioGuard: Toward Comprehensive Audio Safety Protection Across Diverse Threat Models
di: Kang, Mintong, et al.
Pubblicazione: (2026)

Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation
di: Bi, Zhen, et al.
Pubblicazione: (2025)

CodeGuard: Improving LLM Guardrails in CS Education
di: Raihan, Nishat, et al.
Pubblicazione: (2026)

OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
di: Zhu, Boyu, et al.
Pubblicazione: (2025)

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data
di: Zhou, Andy, et al.
Pubblicazione: (2024)

GuardReasoner: Towards Reasoning-based LLM Safeguards
di: Liu, Yue, et al.
Pubblicazione: (2025)

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
di: Kang, Mintong, et al.
Pubblicazione: (2023)

Certifiably Byzantine-Robust Federated Conformal Prediction
di: Kang, Mintong, et al.
Pubblicazione: (2024)

Safety Guardrails for LLM-Enabled Robots
di: Ravichandran, Zachary, et al.
Pubblicazione: (2025)

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
di: Liu, Yue, et al.
Pubblicazione: (2025)

Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning
di: Jiang, Enyi, et al.
Pubblicazione: (2025)

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models
di: Sreedhar, Makesh Narsimhan, et al.
Pubblicazione: (2025)

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
di: Kang, Mintong, et al.
Pubblicazione: (2024)

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection
di: Lin, Lixing, et al.
Pubblicazione: (2026)

Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
di: Xiao, Yilin, et al.
Pubblicazione: (2025)

Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement
di: Xu, Mingyu, et al.
Pubblicazione: (2026)

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
di: Wang, Yaxuan, et al.
Pubblicazione: (2025)

MindGuard: Guardrail Classifiers for Multi-Turn Mental Health Support
di: Farinhas, António, et al.
Pubblicazione: (2026)

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
di: Li, Nanxi, et al.
Pubblicazione: (2026)

ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge
di: Zhao, Zihan, et al.
Pubblicazione: (2025)

DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
di: Jiang, Bo
Pubblicazione: (2026)

An Enhanced Prompt-Based LLM Reasoning Scheme via Knowledge Graph-Integrated Collaboration
di: Li, Yihao, et al.
Pubblicazione: (2024)

Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs
di: Gao, Yisen, et al.
Pubblicazione: (2025)

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection
di: Giarrusso, Francesco, et al.
Pubblicazione: (2025)

Evaluating Robustness of Reasoning Models on Parameterized Logical Problems
di: Es-sebbani, Naïm, et al.
Pubblicazione: (2026)

Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
di: Li, Yanda, et al.
Pubblicazione: (2024)

ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning
di: Luo, Linhao, et al.
Pubblicazione: (2023)

Assessing LLM Reasoning Steps via Principal Knowledge Grounding
di: Hwang, Hyeon, et al.
Pubblicazione: (2025)

Logical Reasoning with Relation Network for Inductive Knowledge Graph Completion
di: Zhang, Qinggang, et al.
Pubblicazione: (2024)

RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts
di: She, Yining, et al.
Pubblicazione: (2025)

Self-Guard: Defending Large Reasoning Models via enhanced self-reflection
di: Zheng, Jingnan, et al.
Pubblicazione: (2026)

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
di: Li, Hao, et al.
Pubblicazione: (2024)

BiasGuard: Guardrailing Fairness in Machine Learning Production Systems
di: Cohen-Inger, Nurit, et al.
Pubblicazione: (2025)

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
di: Nie, Yuzhou, et al.
Pubblicazione: (2025)

Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry
di: Su, Changqing, et al.
Pubblicazione: (2026)

Adaptive Selection of Symbolic Languages for Improving LLM Logical Reasoning
di: Wang, Xiangyu, et al.
Pubblicazione: (2025)

Towards Unifying Perceptual Reasoning and Logical Reasoning
di: Kido, Hiroyuki
Pubblicazione: (2022)

MemR$^3$: Memory Retrieval via Reflective Reasoning for LLM Agents
di: Du, Xingbo, et al.
Pubblicazione: (2025)

Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning
di: Song, Xinyuan, et al.
Pubblicazione: (2025)