Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2311.14782 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915023633252352 |
|---|---|
| author | Niu, Peisong Zhou, Tian Wang, Xue Sun, Liang Jin, Rong |
| author_facet | Niu, Peisong Zhou, Tian Wang, Xue Sun, Liang Jin, Rong |
| contents | In the burgeoning domain of Large Language Models (LLMs), there is a growing interest in applying LLM to time series forecasting, with multiple studies focused on leveraging textual prompts to further enhance the predictive prowess. This study aims to understand how and why the integration of textual prompts into LLM can effectively improve the prediction accuracy of time series, which is not obvious at the glance, given the significant domain gap between texts and time series. Our extensive examination leads us to believe that (a) adding text prompts is roughly equivalent to introducing additional adapters, and (b) It is the introduction of learnable parameters rather than textual information that aligns the LLM with the time series forecasting task, ultimately enhancing prediction accuracy. Inspired by this discovery, we developed four adapters that explicitly address the gap between LLM and time series, and further improve the prediction accuracy. Overall,our work highlights how textual prompts enhance LLM accuracy in time series forecasting and suggests new avenues for continually improving LLM-based time series analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_14782 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Understanding the Role of Textual Prompts in LLM for Time Series Forecasting: an Adapter View Niu, Peisong Zhou, Tian Wang, Xue Sun, Liang Jin, Rong Machine Learning In the burgeoning domain of Large Language Models (LLMs), there is a growing interest in applying LLM to time series forecasting, with multiple studies focused on leveraging textual prompts to further enhance the predictive prowess. This study aims to understand how and why the integration of textual prompts into LLM can effectively improve the prediction accuracy of time series, which is not obvious at the glance, given the significant domain gap between texts and time series. Our extensive examination leads us to believe that (a) adding text prompts is roughly equivalent to introducing additional adapters, and (b) It is the introduction of learnable parameters rather than textual information that aligns the LLM with the time series forecasting task, ultimately enhancing prediction accuracy. Inspired by this discovery, we developed four adapters that explicitly address the gap between LLM and time series, and further improve the prediction accuracy. Overall,our work highlights how textual prompts enhance LLM accuracy in time series forecasting and suggests new avenues for continually improving LLM-based time series analysis. |
| title | Understanding the Role of Textual Prompts in LLM for Time Series Forecasting: an Adapter View |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2311.14782 |