用大模型进化出可解释的代码，零样本解决时序推理问题
EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs
- 用大模型引导演化生成纯Python代码，实现零样本推理
- 单个算法跨数据集通用，速度比深度学习快多个数量级
- 结果可解释且性能媲美甚至超越顶尖深度学习模型
我们提出EVIL（EVolving Interpretable algorithms with LLMs），一种利用大语言模型引导的进化搜索方法，用于发现动态系统推断的简单可解释算法。与在大规模数据上训练神经网络不同，EVIL通过演化生成纯Python/NumPy程序，在不进行每数据集训练的情况下，实现跨数据集的零样本、上下文内推理。该方法应用于三个任务：时间点过程的下一事件预测、马尔可夫跳跃过程的速率矩阵估计以及时间序列插补。在每个任务中，单一演化算法均能泛化至所有测试数据集，无需微调（类似摊销推断模型）。据我们所知，这是首个证明大模型引导程序演化可发现适用于这些动态系统问题的单一紧凑推理函数的工作。在三个领域中，所发现算法通常与现有最先进深度学习模型相当，甚至更优，且速度提升数个数量级，同时保持完全可解释性。
原文摘要 · Abstract (English)
We introduce EVIL (\textbf{EV}olving \textbf{I}nterpretable algorithms with \textbf{L}LMs), an approach that uses LLM-guided evolutionary search to discover simple, interpretable algorithms for dynamical systems inference. Rather than training neural networks on large datasets, EVIL evolves pure Python/NumPy programs that perform zero-shot, in-context inference across datasets. We apply EVIL to three distinct tasks: next-event prediction in temporal point processes, rate matrix estimation for Markov jump processes, and time series imputation. In each case, a single evolved algorithm generalizes across all evaluation datasets without per-dataset training (analogous to an amortized inference model). To the best of our knowledge, this is the first work to show that LLM-guided program evolution can discover a single compact inference function for these dynamical-systems problems. Across the three domains, the discovered algorithms are often competitive with, and even outperform, state-of-the-art deep learning models while being orders of magnitudes faster, and remaining fully interpretable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。