The performance of Large Language Models (LLMs) on many tasks is greatly limited by the knowledge learned during pre-training and stored in the model's parameters. Low-rank adaptation (LoRA) is a popular and efficient training technique for updating or domain-specific adaptation of LLMs. In this study, we investigate how new facts can be incorporated into the LLM using LoRA without compromising the previously learned knowledge. We fine-tuned Llama-3.1-8B-instruct using LoRA with varying amounts of new knowledge. Our experiments have shown that the best results are obtained when the training data contains a mixture of known and new facts. However, this approach is still potentially harmful because the model's performance on external question-answering benchmarks declines after such fine-tuning. When the training data is biased towards certain entities, the model tends to regress to few overrepresented answers. In addition, we found that the model becomes more confident and refuses to provide an answer in only few cases. These findings highlight the potential pitfalls of LoRA-based LLM updates and underscore the importance of training data composition and tuning parameters to balance new knowledge integration and general model capabilities.

翻译：大型语言模型（LLM）在许多任务上的性能很大程度上受限于预训练期间学习并存储于模型参数中的知识。低秩适应（LoRA）是一种流行且高效的训练技术，用于更新LLM或进行领域特定适应。在本研究中，我们探讨了如何在不损害先前所学知识的前提下，使用LoRA将新事实融入LLM。我们使用包含不同数量新知识的训练数据，通过LoRA对Llama-3.1-8B-instruct进行了微调。实验表明，当训练数据混合包含已知事实和新事实时，能获得最佳结果。然而，这种方法仍存在潜在危害，因为经过此类微调后，模型在外部问答基准测试上的性能会下降。当训练数据偏向某些实体时，模型倾向于回归到少数过度代表的答案。此外，我们发现模型变得更加自信，仅在少数情况下拒绝提供答案。这些发现凸显了基于LoRA的LLM更新可能存在的缺陷，并强调了训练数据构成和调优参数对于平衡新知识整合与模型通用能力的重要性。