PPL
Christopher D. Manning
Papers (4)
Direct Preference Optimization: Your Language Model is Secretly a Reward ModelPile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal DatasetShepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution TraceSecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization