3 papers
cs.AI2026
STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA
Xinkang Li, Rong Jiang, Xin Song +3
In open-domain multi-hop question answering (QA), LLM-based search agents offer a promising approach to knowledge-intensive QA by combining retrieval with reasoning. Existing metho…
cs.CL2025
Exemplar-Guided Planing: Enhanced LLM Agent for KGQA
Jingao Xu, Shuoyoucheng Ma, Xin Song +3
Large Language Models (LLMs) as interactive agents show significant promise in Knowledge Graph Question Answering (KGQA) but often struggle with the semantic gap between natural la…
cs.LG2023
MixTEA: Semi-supervised Entity Alignment with Mixture Teaching
Feng Xie, Xin Song, Xiang Zeng +4
Semi-supervised entity alignment (EA) is a practical and challenging task because of the lack of adequate labeled mappings as training data. Most works address this problem by gene…