5 papers
LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks
Zhongyuan Wang, Pratyusha Vemuri
Adding LLM-generated node features to graph neural networks (GNNs) is widely reported to improve accuracy on standard benchmarks. We document a contrasting observation: when LLM fe…
When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More
Zhongyuan Wang, Pratyusha Vemuri
A growing line of work equips large language model (LLM) agents with graph neural networks (GNNs) as callable tools, assuming the agent exercises judgment over when and how much to…
General Table Question Answering via Answer-Formula Joint Generation
Zhongyuan Wang, Richong Zhang, Zhijie Nie +1
Advanced table question answering (TableQA) methods prompt large language models (LLMs) to generate answer text, SQL query, Python code, or custom operation, which impressively imp…
EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations
Zhangchi Feng, Dongdong Kuang, Zhongyuan Wang +3
This paper presents EasyRAG, a simple, lightweight, and efficient retrieval-augmented generation framework for automated network operations. Our framework has three advantages. The…
Tool-Assisted Agent on SQL Inspection and Refinement in Real-World Scenarios
Zhongyuan Wang, Richong Zhang, Zhijie Nie +1
Recent Text-to-SQL methods leverage large language models (LLMs) by incorporating feedback from the database management system. While these methods effectively address execution er…