释放函数向量的力量：表征与缓解持续指令调优中的灾难性遗忘
Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
AI总结：
针对持续指令调优中灾难性遗忘问题，本研究通过分析函数向量发现遗忘受任务和模型双重影响，提出函数向量引导的正则化训练方法，有效缓解遗忘并验证了理论框架。
摘要：
灾难性遗忘（CF）是机器学习中的重大挑战，模型在学习新任务时会忘记先前习得的信息。尽管大语言模型（LLMs）具备先进能力，但在持续学习中仍面临CF问题。现有多数研究通过单一训练序列分析遗忘模式，忽视了多样化任务对模型行为的复杂影响。本研究在多种设置下探索CF，发现模型遗忘受特定训练任务和模型自身双重影响。为此，我们通过函数向量（FV，LLMs中函数的紧凑表示）解释遗忘，提供模型相关的CF发生指标。经理论与实证分析，我们证明LLMs的CF主要源于函数激活偏差，而非任务处理函数的覆盖。基于这些见解，我们提出一种新型函数向量引导的训练方法，纳入正则化技术以稳定FV并缓解遗忘。在四个基准上的实证测试证实了所提训练方法的有效性，验证了我们关于CF和模型函数动态的理论框架。我们计划近期公开代码。
英文摘要：
Catastrophic forgetting (CF) poses a significant challenge in machine learning, where a model forgets previously learned information upon learning new tasks. Despite the advanced capabilities of Large Language Models (LLMs), they continue to face challenges with CF during continual learning. The majority of existing research focuses on analyzing forgetting patterns through a singular training sequence, thereby overlooking the intricate effects that diverse tasks have on model behavior. Our study explores CF across various settings, discovering that model forgetting is influenced by both the specific training tasks and the models themselves. To this end, we interpret forgetting by examining the function vector (FV), a compact representation of functions in LLMs, offering a model-dependent indicator for the occurrence of CF. Through theoretical and empirical analyses, we demonstrated that CF in LLMs primarily stems from biases in function activation rather than the overwriting of task processing functions. Leveraging these insights, we propose a novel function vector guided training methodology, incorporating a regularization technique to stabilize the FV and mitigate forgetting. Empirical tests on four benchmarks confirm the effectiveness of our proposed training method, substantiating our theoretical framework concerning CF and model function dynamics. We plan to make our code publicly accessible in the near future.
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。
