Search-based Optimisation of LLM Learning Shots for Story Point Estimation
This work addresses estimation accuracy for agile development teams, but it is incremental as it applies existing search-based methods to a specific domain.
The paper tackled the problem of improving story point estimation in agile tasks by optimizing the number and combination of examples for few-shot learning with Large Language Models, resulting in a 59.34% average improvement in estimation performance over a zero-shot setting.
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.