nlp:llm_safety

This is an old revision of the document!

Table of Contents

Large Language Model Safety

Large Language Model Safety

Papers

Zou et al 2023 - Representation Engineering: A Top-Down Approach to AI Transparency
Xu et al 2024 - Uncovering Safety Risks in Open-source LLMs through Concept Activation Vector
Wallace et al 2024 - The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Jailbraking LLMs

Overviews
- Yi et al 2024 - Jailbreak Attacks and Defenses Against Large Language Models: A Survey
Wei et al 2023 - Jailbroken: How Does LLM Safety Training Fail?
Zhou et al 2023 - Universal and Transferable Adversarial Attacks on Aligned Language Models
Zhou et al 2024 - EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models
Paulus et al 2024 - AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Related Work

Model Editing

nlp/llm_safety.1741666943.txt.gz · Last modified: 2025/03/11 04:22 by jmflanig