一作ACL 2026Poster· Natural Language Processing
TRN - R 1-Zero: Text-rich Network Reasoning via LLM s with Reinforcement Learning Only
Yilun Liu · Ruihong Qiu · Zi Huang
摘要
Zero-shot reasoning on text-rich networks (TRNs) remains a challenging frontier, as models must integrate textual semantics with relational structure without task-specific supervision. While graph neural networks rely on fixed label spaces and supervised objectives, recent large language model (L...