对齐大型语言模型持续预训练中的遗忘现象研究
Examining Forgetting in Continual Pre-training of Aligned Large Language Models
AI总结：
本文研究了在已微调的大型语言模型上进行持续预训练时发生的灾难性遗忘现象，从输出格式、知识和可靠性等维度评估其影响，发现解决该遗忘问题尤其是重复问题具有重大挑战。
摘要：
大型语言模型（LLMs）的最新进展在各种任务中展现出卓越的能力。鉴于LLMs在众多领域的强大应用，LLM的开发激增。在开发LLMs时，一种常见做法是在先前微调过的模型上进行持续预训练。然而，这可能导致灾难性遗忘。在我们的工作中，我们研究了在现有微调LLM上进行持续预训练时发生的遗忘现象。我们从输出格式、知识和可靠性等多个维度评估了持续预训练对微调LLM的影响。实验结果突显了在持续预训练期间解决灾难性遗忘的重大挑战，特别是重复问题。
英文摘要：
Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developing LLMs, a common practice involves continual pre-training on previously fine-tuned models. However, this can lead to catastrophic forgetting. In our work, we investigate the phenomenon of forgetting that occurs during continual pre-training on an existing fine-tuned LLM. We evaluate the impact of continuous pre-training on the fine-tuned LLM across various dimensions, including output format, knowledge, and reliability. Experiment results highlight the non-trivial challenge of addressing catastrophic forgetting during continual pre-training, especially the repetition issue.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
