作者位次 #4/6ACL 2026Findings· Findings of ACL
CGB ridge: Bridging Code Graphs and Large Language Models for Better Structure-Aware Code Understanding
Zeqi Chen · Zhaoyang Chu · Yi Gui · Feng Guo · Yao Wan · Chuan Shi
摘要
Large Language Models (LLMs) have demonstrated remarkable performance in code intelligence tasks such as code generation, summarization, and translation. However, their reliance on linearized token sequences makes them brittle to long-range program dependencies and superficial lexical shifts such...