用语言模型从时间序列中推断事件，效果出人意料。
Inferring Events from Time Series using Language Models
- 基于体育数据自动生成推理任务，构建新基准
- 小模型经蒸馏+强化学习后逼近大模型表现
- 适合做时序事件理解与模型评估的研究者
分析时间序列数据的常见目标是理解事件如何引起观测变化。我们研究大型语言模型（LLMs）是否能推断与时间序列数据相关的自然语言事件。提出一种自动化方法，基于体育数据生成测试模型事件推理能力的任务，并开发新的评估方法。在涵盖18个LLMs的实验中，给定时间序列数据，模型能在极少上下文条件下成功推断未观察到的事件。进一步证明，通过蒸馏结合强化学习（RL），小型语言模型性能可接近大型专有推理模型。所有复现资源已公开：https://github.com/hartvigsen-group/GAMETime。
原文摘要 · Abstract (English)
A common goal in analyzing time series data is to understand how events cause observed variations. We study whether Large Language Models (LLMs) can infer natural language events associated with time series data. We introduce an automated method for generating tasks that test a model's ability to reason about events associated with time series data based on sports data, and develop a new benchmarking method. In experiments spanning 18 LLMs, we prompt LLMs to infer unobserved events given time series data and observe surprising successes, even when providing minimal context. We then show that combining distillation with Reinforcement Learning (RL) can improve the performance for small language models to approach that of large proprietary reasoning models. All resources needed to reproduce our work are available: https://github.com/hartvigsen-group/GAMETime
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。