ArXiv TLDR

Zac Hatfield-Dodds

3 papers · Latest:

Natural Language Processing

Discovering Language Model Behaviors with Model-Written Evaluations

This paper introduces a method to automatically generate high-quality evaluations using language models themselves, revealing new and unexpected behaviors as models scale.

2212.09251
Natural Language Processing

Constitutional AI: Harmlessness from AI Feedback

Constitutional AI trains harmless AI assistants using AI-generated feedback guided by a set of human-defined principles, minimizing the need for human-labeled data.

2212.08073
Natural Language Processing

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

This paper demonstrates that reinforcement learning from human feedback (RLHF) can effectively fine-tune language models to be both helpful and harmless, improving performance across NLP tasks while maintaining specialized skills.

2204.05862

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.