Overcoming the Modality Gap in Context-Aided Forecasting
Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal models often fail to outperform their unimodal counterparts. We hypothesize that this underperformance stems from poor context quality in existing datasets, as verification is challenging. To address these limitations, we introduce a semi-synthetic data augmentation method that generates contexts both descriptive of temporal dynamics and verifiably complementary to numerical histories. This approach enables massive-scale dataset creation, resulting in CAF-7M, a corpus of 7 million context-augmented time series windows, including a rigorously verified test set. We demonstrate that semi-synthetic pre-training transfers effectively to real-world evaluation, and show clear evidence of context utilization. Our results suggest that dataset quality, rather than architectural limitations, has been the primary bottleneck in context-aided forecasting.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSimilar Papers 제목 키워드 기반
Beyond Naïve Prompting: Strategies for Improved Context-aided Forecasting with LLMs
Real-world forecasting requires models to integrate not only historical data but also relevant contextual information provided in textual form. While large language models (LLMs) show promise for context-aided forecastin…
Dr-CiK: A Testbed for Foresight-Driven Agents
Time series forecasting in real-world settings often depends not only on historical observations, but also on external context that must be actively discovered from noisy, heterogeneous information sources. Yet existing …
Time Series ForecastingUniCast: A Unified Framework for Instance-Conditioned Multimodal Time-Series Forecasting
Time series forecasting underpins applications in finance, healthcare, and environmental monitoring. Despite the success of Time Series Foundation Models (TSFMs), existing approaches operate in a unimodal setting and rel…
Time Series ForecastingUnder the Hood of Transformer Networks for Trajectory Forecasting
Transformer Networks have established themselves as the de-facto state-of-the-art for trajectory forecasting but there is currently no systematic study on their capability to model the motion patterns of people, without …
Trajectory ForecastingText-centric Alignment for Multi-Modality Learning
This research paper addresses the challenge of modality mismatch in multimodal learning, where the modalities available during inference differ from those available at training. We propose the Text-centric Alignment for …
In-Context Learning