LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.
L., Phang, J., Bowman, S
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2023 3verdicts
UNVERDICTED 3representative citing papers
Self-Debugging teaches LLMs to identify and fix their own code errors through rubber-duck-style natural language explanations and execution feedback, delivering 2-12% gains over baselines on Spider, TransCoder, and MBPP.
PaLM 2 reports state-of-the-art results on language, reasoning, and multilingual tasks with improved efficiency over PaLM.
citing papers explorer
-
Jailbroken: How Does LLM Safety Training Fail?
LLM safety training fails due to competing objectives and mismatched generalization, enabling new jailbreaks that succeed on all unsafe prompts from red-teaming sets in GPT-4 and Claude.
-
Teaching Large Language Models to Self-Debug
Self-Debugging teaches LLMs to identify and fix their own code errors through rubber-duck-style natural language explanations and execution feedback, delivering 2-12% gains over baselines on Spider, TransCoder, and MBPP.
-
PaLM 2 Technical Report
PaLM 2 reports state-of-the-art results on language, reasoning, and multilingual tasks with improved efficiency over PaLM.