Skip to content
conftrace_

token-level proximal policy optimization

1 paper

Explore in graph

Also known as

TPPO

Co-occurring keywords · papers mentioning both

sparse reward modeling (1) token-level optimization (1) reinforcement learning from ai feedback (1) large language model fine-tuning (1) user intent (1) query generation (1) reward model (1) reinforcement learning (1)

Papers

Token-level Proximal Policy Optimization for Query Generation EMNLP 2025