KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
Abstract
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.
Authors 9
-
Shandong University · University of Amsterdam
Affiliation as printed
Shandong University , Qingdao , China
University of Amsterdam , Amsterdam , The Netherlands
-
Affiliation as printed
Baidu Inc. , Beijing , China
-
Affiliation as printed
Baidu Inc. , Beijing , China
-
Affiliation as printed
Baidu Inc. , Beijing , China
-
Affiliation as printed
Baidu Inc. , Beijing , China
-
Affiliation as printed
Shandong University , Qingdao , China
-
Affiliation as printed
Shandong University , Qingdao , China
-
Affiliation as printed
University of Amsterdam , Amsterdam , The Netherlands
-
Zhaochun Ren Aachen
Affiliation as printed
Leiden University , Leiden , The Netherlands
Cited by 1 stored of 1
1 result
No patents citing this paper on Lens.org (checked 2026-10-11).