activity
20222026
most citedPrinciple-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision

63 citations · 153 across the 15 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CL2026

What Is Missing: Interpretable Ratings for Large Language Model Outputs

Nicholas Stranges, Yimin Yang

Current Large Language Model (LLM) preference learning methods such as Proximal Policy Optimization and Direct Preference Optimization learn from direct rankings or numerical ratin…