TSFM Meets LLM: Context as Covariates

Author1, Author2, Author3, Author4, Author5

multimodalforecastingfine-tuningcovariates

2611.05515

Builder Relevance

80%

2h ago

Abstract

This paper proposes a framework that combines Large Language Models and Time Series Foundation Models to enhance forecasting accuracy by using textual information as covariates.

Reality Card

Core Claim

The proposed CoCo framework achieves up to 12% MAE improvement over state-of-the-art TSFMs and LLM forecasters by effectively integrating textual reasoning into numerical forecasting.

Method / Result

Achieved up to 12% MAE improvement over state-of-the-art models.

Limitations

The reliance on large-scale paired multimodal datasets may limit reproducibility.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.

← Back to all papers