Skip to content
conftrace_

implicit reward margin

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

preference bootstrapping (1) alignment potential (1) explicit reward margin (1) self-play data generation (1) off-policy data (1) reward margin (1) reinforcement learning from human feedback (1) instruction following (1) direct preference optimization (1) preference learning (1)

Papers

Larger or Smaller Reward Margins to Select Preferences for LLM Alignment? ICML 2025 SeRA: Self-Reviewing and Alignment of LLMs using Implicit Reward Margins ICLR 2025