← Search

Hui Cai

2 accepted papers

2024

Efficient Knowledge Infusion via KG-LLM Alignment

ACL 2024findings

To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion. However, existing approaches face two primary challenges: knowledge mismatch b…

2024

Reverse Chain: A Generic-Rule for LLMs to Master Multi-API Planning

NAACL 2024findings

While enabling large language models to implement function calling (known as APIs) can greatly enhance the performance of Large Language Models (LLMs), function calling is still a challenging task due to the complicated relations between different APIs, especially in a context-learning setting witho…