KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
This addresses limitations in generating incomplete, non-factual, or illogical answers for knowledge-intensive tasks like question answering, though it appears incremental as it builds on existing fine-tuning approaches.
The paper tackles the problem of large language models struggling with knowledge-intensive tasks by proposing KnowTuning, a knowledge-aware fine-tuning method that improves fine-grained and coarse-grained knowledge awareness, resulting in more facts generated with a lower factual error rate in evaluations.
Despite their success at many natural language processing (NLP) tasks, large language models 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 improve fine-grained and coarse-grained knowledge awareness of LLMs. We devise a fine-grained knowledge augmentation stage to train LLMs to identify difficult fine-grained knowledge in answers. We also propose a coarse-grained knowledge comparison stage to train LLMs to distinguish between reliable and unreliable knowledge, in three aspects: completeness, factuality, and logicality. Extensive experiments on both generic and medical question answering (QA) datasets confirm the effectiveness of KnowTuning, through automatic and human evaluations, across various sizes of LLMs. We further verify that KnowTuning generates more facts with less factual error rate under fine-grained facts evaluation.