Prompting Underestimates LLM Capability for Time Series Classification
Prompt-based evaluations suggest that large language models (LLMs) perform poorly on time series classification, raising doubts about whether they encode meaningful temporal structure. We show that this conclusion reflects limitations of prompt-based generation rather than the model's representational capacity by directly comparing prompt outputs with linear probes over the same internal representations. While zero-shot prompting performs near chance, linear probes improve average F1 from 0.15-0.26 to 0.61-0.67, often matching or exceeding specialized time series models. Layer-wise analyses further show that class-discriminative time series information emerges in early transformer layers and is amplified by visual and multimodal inputs. Together, these results demonstrate a systematic mismatch between what LLMs internally represent and what prompt-based evaluation reveals, leading current evaluations to underestimate their time series understanding.
Code (0)
등록된 구현이 없습니다.
Tasks
Time Series ClassificationSimilar Papers 제목 키워드 기반
Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding
Automated International Classification of Diseases (ICD) coding is a core medical-coding task for billing, epidemiology, and clinical decision support. Generative large language models (LLMs) are often reported as weak m…
Reinforcement LearningHierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification
Leveraging large language models (LLMs) has garnered increasing attention and introduced novel perspectives in time series classification. However, existing approaches often overlook the crucial dynamic temporal informat…
Text GenerationTime SeriesTime Series AnalysisTime Series ClassificationTime2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting
Large language models (LLMs) show promise for health applications when combined with behavioral sensing data. Traditional approaches convert sensor data into text prompts, but this process is prone to errors, computation…
Time SeriesTask-Aware Mixture-of-Experts for Time Series Analysis
Time Series Analysis is widely used in various real-world applications such as weather forecasting, financial fraud detection, imputation for missing data in IoT systems, and classification for action recognization. Mixt…
Time Series AnalysisWeather ForecastingFraud DetectionGraph Neural Alchemist: An innovative fully modular architecture for time series-to-graph classification
This paper introduces a novel Graph Neural Network (GNN) architecture for time series classification, based on visibility graph representations. Traditional time series classification methods often struggle with high com…
Graph ClassificationGraph Neural NetworkTime SeriesTime Series Analysis+1