Cover Image

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Seungju, Rao, Kavel, Ettinger, Allyson, Jiang, Liwei, Lin, Bill Yuchen, Lambert, Nathan, Choi, Yejin, Dziri, Nouha
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
by: Jiang, Liwei, et al.
Published: (2024)

What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations
by: Rao, Kavel, et al.
Published: (2023)

AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
by: Lu, Ximing, et al.
Published: (2024)

WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
by: Lin, Bill Yuchen, et al.
Published: (2024)

To Err is AI : A Case Study Informing LLM Flaw Reporting Practices
by: McGregor, Sean, et al.
Published: (2024)

SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior
by: Li, Jing-Jing, et al.
Published: (2024)

Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties
by: Sorensen, Taylor, et al.
Published: (2023)

TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities
by: Graf, Victoria, et al.
Published: (2026)

CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Prompting
by: Li, Huihan, et al.
Published: (2024)

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
by: Jiang, Liwei, et al.
Published: (2025)

PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
by: Kumar, Priyanshu, et al.
Published: (2025)

RewardBench: Evaluating Reward Models for Language Modeling
by: Lambert, Nathan, et al.
Published: (2024)

Surfacing Semantic Orthogonality Across Model Safety Benchmarks: A Multi-Dimensional Analysis
by: Bennion, Jonathan, et al.
Published: (2025)

WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
by: Lu, Yujie, et al.
Published: (2024)

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety
by: Vijayvargiya, Sanidhya, et al.
Published: (2025)

Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks
by: Ham, Seokil, et al.
Published: (2025)

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
by: Qiu, Linlu, et al.
Published: (2023)

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
by: Asif, Sadia, et al.
Published: (2026)

WildVis: Open Source Visualizer for Million-Scale Chat Logs in the Wild
by: Deng, Yuntian, et al.
Published: (2024)

Multi-Attribute Constraint Satisfaction via Language Model Rewriting
by: Baheti, Ashutosh, et al.
Published: (2024)

A Roadmap to Pluralistic Alignment
by: Sorensen, Taylor, et al.
Published: (2024)

Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently
by: Misra, Kanishka, et al.
Published: (2024)

When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models
by: Li, Yanhong, et al.
Published: (2024)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
by: Xu, Zhangchen, et al.
Published: (2024)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

Agent Lumos: Unified and Modular Training for Open-Source Language Agents
by: Yin, Da, et al.
Published: (2023)

ColorGrid: A Multi-Agent Non-Stationary Environment for Goal Inference and Assistance
by: Risukhin, Andrey, et al.
Published: (2025)

BingoGuard: LLM Content Moderation Tools with Risk Levels
by: Yin, Fan, et al.
Published: (2025)

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
by: Hu, Xulin, et al.
Published: (2026)

HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions
by: Zhou, Xuhui, et al.
Published: (2024)

Don't Say No: Jailbreaking LLM by Suppressing Refusal
by: Zhou, Yukai, et al.
Published: (2024)

In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
by: Li, Zhuofeng, et al.
Published: (2025)

Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use
by: Agarwal, Aradhye, et al.
Published: (2026)

DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life
by: Chiu, Yu Ying, et al.
Published: (2024)

ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts
by: Aswal, Darpan, et al.
Published: (2025)

GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
by: Zhang, Peiyan, et al.
Published: (2025)

RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMs
by: Nguyen, Tuan T., et al.
Published: (2025)

Linking the religious and social environment to sexual minority mental health
by: Nathan R. Todd, et al.
Published: (2025)

X-Guard: Multilingual Guard Agent for Content Moderation
by: Upadhayay, Bibek, et al.
Published: (2025)

Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation
by: Wróbel, Krzysztof, et al.
Published: (2026)