作者位次 #8/10ACL 2026Poster· Natural Language Processing
Enhancing Agentic Textual Graph Retrieval with Synthetic Stepwise Supervision
Ge Chang · Jinbo Su · Jiacheng Liu · Pengfei Yang · Yuhao Shang · Huiwen Zheng · Hongli Ma · Yan Liang · Yuanchun Li · Yunxin Liu
摘要
Integrating textual graphs into Large Language Models (LLMs) is promising for complex graph-based QA. However, a key bottleneck is retrieving informative yet compact subgraphs that fit the LLM context. Existing retrievers often struggle, relying either on shallow embedding similarity or costly in...