Search-based Optimisation of LLM Learning Shots for Story Point Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916158494474240 |
|---|---|
| author | Tawosi, Vali Alamir, Salwa Liu, Xiaomo |
| author_facet | Tawosi, Vali Alamir, Salwa Liu, Xiaomo |
| contents | One of the ways Large Language Models (LLMs) are used to perform machine learning tasks is to provide them with a few examples before asking them to produce a prediction. This is a meta-learning process known as few-shot learning. In this paper, we use available Search-Based methods to optimise the number and combination of examples that can improve an LLM's estimation performance, when it is used to estimate story points for new agile tasks. Our preliminary results show that our SBSE technique improves the estimation performance of the LLM by 59.34% on average (in terms of mean absolute error of the estimation) over three datasets against a zero-shot setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08430 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Search-based Optimisation of LLM Learning Shots for Story Point Estimation Tawosi, Vali Alamir, Salwa Liu, Xiaomo Software Engineering Artificial Intelligence One of the ways Large Language Models (LLMs) are used to perform machine learning tasks is to provide them with a few examples before asking them to produce a prediction. This is a meta-learning process known as few-shot learning. In this paper, we use available Search-Based methods to optimise the number and combination of examples that can improve an LLM's estimation performance, when it is used to estimate story points for new agile tasks. Our preliminary results show that our SBSE technique improves the estimation performance of the LLM by 59.34% on average (in terms of mean absolute error of the estimation) over three datasets against a zero-shot setting. |
| title | Search-based Optimisation of LLM Learning Shots for Story Point Estimation |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2403.08430 |