conftrace_

length-regularized reward

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

iterative direct preference optimization (1) difficulty aware advantage reweighting (1) reward sparsity (1) concise reasoning (1) group relative policy optimization (1) numerical reasoning (1) conversational question answering (1) mathematical reasoning (1) reinforcement learning (1)

Papers

GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models EMNLP 2025 Investigating the effectiveness of length based rewards in DPO for building Conversational Financial Question Answering Systems COLING 2025