← Search

Zijie Zhong

2 accepted papers

2025

Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation

COLING 2025main

Integrating information from various reference databases is a major challenge for Retrieval-Augmented Generation (RAG) systems because each knowledge source adopts a unique data structure and follows different conventions. Retrieving from multiple knowledge sources with one fixed strategy usually le…

2025

SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task

COLING 2025main

Integrating Large Language Models (LLMs) with existing Knowledge Graph (KG) databases presents a promising avenue for enhancing LLMs’ efficacy and mitigating their “hallucinations”. Given that most KGs reside in graph databases accessible solely through specialized query languages (e.g., Cypher), it…