From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Lehui, Wang, Yuyao, Yan, Jisheng, Zhang, Wei, Deng, Jinliang, Sun, Haoliang, Han, Zhongyi, Gong, Yongshun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912966976208896
author Li, Lehui
Wang, Yuyao
Yan, Jisheng
Zhang, Wei
Deng, Jinliang
Sun, Haoliang
Han, Zhongyi
Gong, Yongshun
author_facet Li, Lehui
Wang, Yuyao
Yan, Jisheng
Zhang, Wei
Deng, Jinliang
Sun, Haoliang
Han, Zhongyi
Gong, Yongshun
contents Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fusion: textual descriptions express temporal impacts implicitly and qualitatively, whereas forecasting models rely on explicit and quantitative signals. Through controlled semi-synthetic experiments, we show that existing methods over-attend to redundant tokens and struggle to reliably translate textual semantics into usable numerical cues. To bridge this gap, we propose TESS, which introduces a Temporal Evolution Semantic Space as an intermediate bottleneck between modalities. This space consists of interpretable, numerically grounded temporal primitives (mean shift, volatility, shape, and lag) extracted from text by an LLM via structured prompting and filtered through confidence-aware gating. Experiments on four real-world datasets demonstrate up to a 29 percent reduction in forecasting error compared to state-of-the-art unimodal and multimodal baselines. The code will be released after acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12664
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
Li, Lehui
Wang, Yuyao
Yan, Jisheng
Zhang, Wei
Deng, Jinliang
Sun, Haoliang
Han, Zhongyi
Gong, Yongshun
Computation and Language
Artificial Intelligence
Incorporating textual information into time-series forecasting holds promise for addressing event-driven non-stationarity; however, a fundamental modality gap hinders effective fusion: textual descriptions express temporal impacts implicitly and qualitatively, whereas forecasting models rely on explicit and quantitative signals. Through controlled semi-synthetic experiments, we show that existing methods over-attend to redundant tokens and struggle to reliably translate textual semantics into usable numerical cues. To bridge this gap, we propose TESS, which introduces a Temporal Evolution Semantic Space as an intermediate bottleneck between modalities. This space consists of interpretable, numerically grounded temporal primitives (mean shift, volatility, shape, and lag) extracted from text by an LLM via structured prompting and filtered through confidence-aware gating. Experiments on four real-world datasets demonstrate up to a 29 percent reduction in forecasting error compared to state-of-the-art unimodal and multimodal baselines. The code will be released after acceptance.
title From Text to Forecasts: Bridging Modality Gap with Temporal Evolution Semantic Space
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2603.12664