3 papers
cs.CL2026
Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG
Manzong Huang, Chenyang Bu, Yi He +2
Graph-based Retrieval-Augmented Generation (GraphRAG) mitigates hallucinations in Large Language Models (LLMs) by grounding them in structured knowledge. However, current GraphRAG…
cs.HC2025
Reject or Not?: A Benchmark for Voice Assistant Query Rejection in Smart Home Scenario and an Improved Method Based on LLMs
Huichao Men, Yizhen Hu, Yingyang He +3
In smart-home voice assistant scenario, deciding whether to accept or reject a user query is the first step before any downstream processing. To address the limited query-rejection…
cs.AI2025
How to Mitigate Information Loss in Knowledge Graphs for GraphRAG: Leveraging Triple Context Restoration and Query-Driven Feedback
Manzong Huang, Chenyang Bu, Yi He +1
Knowledge Graph (KG)-augmented Large Language Models (LLMs) have recently propelled significant advances in complex reasoning tasks, thanks to their broad domain knowledge and cont…