作者位次 #4/6ACL 2026Findings· Findings of ACL
TRAC : Token-level Reward Assignment for Coherent Abstractive Summarization
Xuanqi Chen · 容梓莹 · Xinfeng Liao · Lianxi Wang · Ying Gao · Shengyi Jiang
摘要
Large Language Models (LLMs) have achieved remarkable success in text summarization, particularly through the integration of reinforcement learning. However, maintaining logical coherence and contextual consistency remains a pervasive challenge in long-form generation, often hindering the product...