CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914491999977472 |
|---|---|
| author | Tajeuna, Etienne Owusu, Patrick Asante Brun, Armelle Wang, Shengrui |
| author_facet | Tajeuna, Etienne Owusu, Patrick Asante Brun, Armelle Wang, Shengrui |
| contents | In this paper we investigate forecasting coevolving time series that feature intricate dependencies and nonstationary dynamics by using an LLM Large Language Models approach We propose a novel modeling approach named ContextAware ARLLM CAARL that provides an interpretable framework to decode the contextual dynamics influencing changes in coevolving series CAARL decomposes time series into autoregressive segments constructs a temporal dependency graph and serializes this graph into a narrative to allow processing by LLM This design yields a chainofthoughtlike reasoning path where intermediate steps capture contextual dynamics and guide forecasts in a transparent manner By linking prediction to explicit reasoning traces CAARL enhances interpretability while maintaining accuracy Experiments on realworld datasets validate its effectiveness positioning CAARL as a competitive and interpretable alternative to stateoftheart forecasting methods |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18305 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting Tajeuna, Etienne Owusu, Patrick Asante Brun, Armelle Wang, Shengrui Machine Learning In this paper we investigate forecasting coevolving time series that feature intricate dependencies and nonstationary dynamics by using an LLM Large Language Models approach We propose a novel modeling approach named ContextAware ARLLM CAARL that provides an interpretable framework to decode the contextual dynamics influencing changes in coevolving series CAARL decomposes time series into autoregressive segments constructs a temporal dependency graph and serializes this graph into a narrative to allow processing by LLM This design yields a chainofthoughtlike reasoning path where intermediate steps capture contextual dynamics and guide forecasts in a transparent manner By linking prediction to explicit reasoning traces CAARL enhances interpretability while maintaining accuracy Experiments on realworld datasets validate its effectiveness positioning CAARL as a competitive and interpretable alternative to stateoftheart forecasting methods |
| title | CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.18305 |