conftrace_

gradient reward policy optimization

1 paper

Explore in graph

Also known as

GRPO

Co-occurring keywords · papers mentioning both

large language model (1) data construction (1) structured data extraction (1) data construction pipeline (1) process reward modeling (1) structured reasoning (1) structured data (1) process reward (1) policy optimization (1) reward modeling (1)

Papers

LLMSR@XLLM25: A Language Model-Based Pipeline for Structured Reasoning Data Construction ACL 2025