conftrace_

on-policy sampling

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

direct preference optimization (1) language model alignment (1) reward model (1) data efficiency (1) monte carlo estimator (1) preference data (1) iterative training (1) alignment training (1) preference fine-tuning (1) categorical distribution (1)

Papers

Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization ACL 2025 Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data ICML 2024 Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning NeurIPS 2022