Reasoning on Efficient Knowledge Paths:Knowledge Graph Guides Large Language Model for Domain Question Answering

arXiv:2404.10384v1 Announce Type: new
Abstract: Large language models (LLMs), such as GPT3.5, GPT4 and LLAMA2 perform surprisingly well and outperform human experts on many tasks. However, in many domain-specific evaluations, these LLMs often suffer from hallucination problems due to insufficient training of relevant corpus. Furthermore, fine-tuning large models may face problems such as the LLMs are not open source or the construction of high-quality domain instruction is difficult. Therefore, structured knowledge databases such as knowledge graph can better provide domain …

abstract arxiv cs.ai cs.cl cs.ir domain experts fine-tuning gpt3 gpt3.5 gpt4 graph guides hallucination however human knowledge knowledge graph language language model language models large language large language model large language models llama2 llms question question answering reasoning tasks training type