Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization
This addresses the issue of poor generalization and trade-offs in existing methods for mitigating factual hallucinations in LLMs, which can mislead users, though it is incremental in nature.
The paper tackles the problem of factual hallucinations in Large Language Models by proposing PKUE, a method that enhances precise knowledge utilization through fine-tuning on self-generated responses, resulting in significant improvements in overall performance across various tasks and languages.
Large Language Models (LLMs) often struggle to align their responses with objective facts, resulting in the issue of factual hallucinations, which can be difficult to detect and mislead users without relevant knowledge. Although post-training techniques have been employed to mitigate the issue, existing methods usually suffer from poor generalization and trade-offs in other different capabilities. In this paper, we propose to address these by directly augmenting LLM's fundamental ability to precisely leverage its knowledge and introduce PKUE (Precise Knowledge Utilization Enhancement), which fine-tunes the model on self-generated responses to precise and simple factual questions through preference optimization. Furthermore, we construct FactualBench, a comprehensive and precise factual QA dataset containing 181k Chinese data spanning 21 domains, to facilitate both evaluation and training. Extensive experiments demonstrate that PKUE significantly improves LLM overall performance, with consistent enhancement across factual tasks of various forms, general tasks beyond factuality, and tasks in different language.