这篇论文提出了两种新方法，能减少大模型幻觉，特别适合关注模型可靠性的研究者。
该研究探讨了监督微调(SFT)中目标响应可能引发模型幻觉的问题。研究团队在Qwen 3 4B和OLMo 3 7B模型上测试了知识对齐SFT方法。实验显示，该方法在WildHalu和Biography基准上减少了事实性幻觉，同时保留了模型通用能力。Recall Rewrite方法在UnknownBench上表现出最强的拒绝行为改进。
Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning
Supervised fine-tuning (SFT) trains a base language model to imitate target responses, and these targets may require knowledge the base model has not robustly internalized. We study this as a source of hallucinations and frame a group of mitigation methods as \emph{knowledge-aligned SFT}: constraining SFT training targets to the base model's parametric knowledge. Under a unified setup, we compare existing generation-based and estimation-based knowledge-alignment methods and introduce two new variants: Evidence Rewrite, which verifies base-model generations using external evidence, and Recall Rewrite, which retains claims only when they can be consistently recalled by the base model. Experiments with Qwen 3 4B and OLMo 3 7B show that knowledge-aligned SFT can reduce factual hallucinations on WildHalu and Biography while largely preserving general capabilities. Recall Rewrite yields the strongest factuality gains and improves refusal behavior on UnknownBench. It thereby confirms that SFT targets beyond the base model's knowledge drive hallucination behavior.