Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2405.06703 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929339575042048 |
|---|---|
| author | Muric, Goran Delay, Ben Minton, Steven |
| author_facet | Muric, Goran Delay, Ben Minton, Steven |
| contents | In this paper, we introduce the Interpretable Cross-Examination Technique (ICE-T), a novel approach that leverages structured multi-prompt techniques with Large Language Models (LLMs) to improve classification performance over zero-shot and few-shot methods. In domains where interpretability is crucial, such as medicine and law, standard models often fall short due to their "black-box" nature. ICE-T addresses these limitations by using a series of generated prompts that allow an LLM to approach the problem from multiple directions. The responses from the LLM are then converted into numerical feature vectors and processed by a traditional classifier. This method not only maintains high interpretability but also allows for smaller, less capable models to achieve or exceed the performance of larger, more advanced models under zero-shot conditions. We demonstrate the effectiveness of ICE-T across a diverse set of data sources, including medical records and legal documents, consistently surpassing the zero-shot baseline in terms of classification metrics such as F1 scores. Our results indicate that ICE-T can be used for improving both the performance and transparency of AI applications in complex decision-making environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06703 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Interpretable Cross-Examination Technique (ICE-T): Using highly informative features to boost LLM performance Muric, Goran Delay, Ben Minton, Steven Computation and Language Artificial Intelligence Machine Learning In this paper, we introduce the Interpretable Cross-Examination Technique (ICE-T), a novel approach that leverages structured multi-prompt techniques with Large Language Models (LLMs) to improve classification performance over zero-shot and few-shot methods. In domains where interpretability is crucial, such as medicine and law, standard models often fall short due to their "black-box" nature. ICE-T addresses these limitations by using a series of generated prompts that allow an LLM to approach the problem from multiple directions. The responses from the LLM are then converted into numerical feature vectors and processed by a traditional classifier. This method not only maintains high interpretability but also allows for smaller, less capable models to achieve or exceed the performance of larger, more advanced models under zero-shot conditions. We demonstrate the effectiveness of ICE-T across a diverse set of data sources, including medical records and legal documents, consistently surpassing the zero-shot baseline in terms of classification metrics such as F1 scores. Our results indicate that ICE-T can be used for improving both the performance and transparency of AI applications in complex decision-making environments. |
| title | Interpretable Cross-Examination Technique (ICE-T): Using highly informative features to boost LLM performance |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2405.06703 |