3 papers
cs.CL2025
Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA
Qingyun Jin, Xiaohui Song, Feng Zhou +1
Large language models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, as the model size and the input sequence's length…
cs.AI2025
SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task
Ziije Zhong, Linqing Zhong, Zhaoze Sun +3
Integrating Large Language Models (LLMs) with existing Knowledge Graph (KG) databases presents a promising avenue for enhancing LLMs' efficacy and mitigating their "hallucinations"…
cs.LG2025
Mix-of-Granularity: Optimize the Chunking Granularity for Retrieval-Augmented Generation
Zijie Zhong, Hanwen Liu, Xiaoya Cui +2
Integrating information from various reference databases is a major challenge for Retrieval-Augmented Generation (RAG) systems because each knowledge source adopts a unique data st…