KnowTuning: Knowledge-aware Fine-tuning for Large Language Models

arXiv:2402.11176v1 Announce Type: new
Abstract: Despite their success at many natural language processing (NLP) tasks, large language models (LLMs) still struggle to effectively leverage knowledge for knowledge-intensive tasks, manifesting limitations such as generating incomplete, non-factual, or illogical answers. These limitations stem from inadequate knowledge awareness of LLMs during vanilla fine-tuning. To address these problems, we propose a knowledge-aware fine-tuning (KnowTuning) method to explicitly and implicitly improve the knowledge awareness of LLMs. We devise an explicit knowledge-aware generation stage to train …

abstract arxiv cs.ai cs.cl fine-tuning knowledge language language models language processing large language large language models limitations llms natural natural language natural language processing nlp processing stem struggle success tasks type