Cover Image

Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hu, Wenbin, Jing, Huihao, Shi, Haochen, Li, Haoran, Song, Yangqiu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset
by: Hu, Wenbin, et al.
Published: (2026)

ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance
by: Li, Haoran, et al.
Published: (2026)

Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning
by: Hu, Wenbin, et al.
Published: (2025)

Node Level Graph Autoencoder: Unified Pretraining for Textual Graph Learning
by: Hu, Wenbin, et al.
Published: (2024)

MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning
by: Jing, Huihao, et al.
Published: (2025)

PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance
by: Li, Haoran, et al.
Published: (2025)

MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol
by: Jing, Huihao, et al.
Published: (2025)

Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
by: Wang, Qineng, et al.
Published: (2024)

PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization
by: Jing, Huihao, et al.
Published: (2026)

A Retrieval-Augmented Language Assistant for Unmanned Aircraft Safety Assessment and Regulatory Compliance
by: Immordino, Gabriele, et al.
Published: (2026)

SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation
by: Liu, Xiaoze, et al.
Published: (2024)

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models
by: Tan, Xingwei, et al.
Published: (2026)

GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety
by: Fan, Changxuan, et al.
Published: (2026)

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules
by: Wu, Di, et al.
Published: (2026)

Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
by: Xu, Baixuan, et al.
Published: (2025)

LLM-Based Robust Product Classification in Commerce and Compliance
by: Gholamian, Sina, et al.
Published: (2024)

ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain
by: Zhao, Haochen, et al.
Published: (2024)

Safety Alignment via Constrained Knowledge Unlearning
by: Shi, Zesheng, et al.
Published: (2025)

An Agentic LLM Framework for Adverse Media Screening in AML Compliance
by: Chernakov, Pavel, et al.
Published: (2025)

Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs
by: Momcilovic, Tomas Bueno, et al.
Published: (2024)

Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
by: Brito, Iago Alves, et al.
Published: (2026)

Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation
by: Bai, Jiaxin, et al.
Published: (2023)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
by: Qian, Chen, et al.
Published: (2025)

Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs
by: Fang, Tianqing, et al.
Published: (2024)

Do Reasoning Models Enhance Embedding Models?
by: Chan, Wun Yu, et al.
Published: (2026)

Understanding Inter-Session Intentions via Complex Logical Reasoning
by: Bai, Jiaxin, et al.
Published: (2023)

Safety Reasoning with Guidelines
by: Wang, Haoyu, et al.
Published: (2025)

ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
by: Li, Changyi, et al.
Published: (2025)

Evaluating Plan Compliance in Autonomous Programming Agents
by: Liu, Shuyang, et al.
Published: (2026)

AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph
by: Wang, Zhaowei, et al.
Published: (2023)

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge
by: In, Yeonjun, et al.
Published: (2025)

Evaluating Metrics for Safety with LLM-as-Judges
by: Clegg, Kester, et al.
Published: (2025)

CodeGraph: Enhancing Graph Reasoning of LLMs with Code
by: Cai, Qiaolong, et al.
Published: (2024)

Advancing Risk and Quality Assurance: A RAG Chatbot for Improved Regulatory Compliance
by: Hillebrand, Lars, et al.
Published: (2025)

Different Paths to Harmful Compliance: Behavioral Side Effects and Mechanistic Divergence Across LLM Jailbreaks
by: Kabir, Md Rysul, et al.
Published: (2026)

SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning
by: Xu, Tianyang, et al.
Published: (2025)

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

How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
by: Zeng, Yi, et al.
Published: (2024)

Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis
by: Song, Da, et al.
Published: (2026)

Ustnlp16 at SemEval-2025 Task 9: Improving Model Performance through Imbalance Handling and Focal Loss
by: Cai, Zhuoang, et al.
Published: (2025)