arXiv cs.AI· Md Atik Ahamed, Mihir Parmar, Palash Goyal, Chun-Liang Li, Qiang Cheng, Tomas Pfister, Jinsung Yoon·· 12 小时前AI 评分34
STRIDE：面向时间序列预测的推理感知训练框架
STRIDE: Reasoning-Aware Training for Time Series Forecasting
AI 导读
STRIDE 框架将 LLM 推理轨迹蒸馏进轻量 LLM，并把其池化隐藏状态作为连续跨模态先验注入时间序列基础模型的数值编码器，避免文本 tokenizer 切碎连续数值。
正文 · 原文
Abstract:Time Series Foundation Models (TSFMs) excel at numerical forecasting but operate as black boxes lacking qualitative reasoning. Conversely, applying LLMs directly to temporal data introduces a modality gap: text tokenizers fragment continuous numerical values, degrading mathematical relationships and exploding sequence lengths, leading to computational overhead. To resolve this, we introduce STRIDE (Strategic Time-series Reasoning Injected via Distilled Embeddings), a novel framework natively integrating LLM reasoning into the continuous embedding space of TSFMs. Instead of discrete tokens, STRIDE distills reasoning traces into a lightweight LLM and dynamically projects its pooled hidden states as a continuous cross-modal prior into the numerical encoder. Jointly optimized via cross-entropy and quantile losses, STRIDE readily attaches to diverse architectures (e.g., Chronos-2, Timer-S1). STRIDE ranks #1 on the GIFT-Eval leaderboard (0.625 MASE, 0.423 CRPS) when ensembled with Synapse. On TFRBench, STRIDE consistently outperforms baselines in both forecasting accuracy and reasoning quality, with ablations confirming gains stem from strategic reasoning. Thus, injecting semantic reasoning as a continuous prior equips TSFMs with human-interpretable reasoning while improving predictive accuracy.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.08625 [cs.LG] |
| (or arXiv:2605.08625v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08625 arXiv-issued DOI via DataCite |
Submission history
From: Md Atik Ahamed [view email]
[v1]
Sat, 9 May 2026 02:41:47 UTC (2,608 KB)
[v2]
Fri, 16 Oct 2026 04:26:36 UTC (3,870 KB)
来源：arXiv cs.AI · arxiv.org