# Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT

arXiv: https://arxiv.org/abs/2311.11547 · HTML: https://mlsanity.com/paper/2311.11547/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 19 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 3 of 3)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Are "Non-functional" Requirements really Non-functional?](https://mlsanity.com/paper/1611.08868/) (2016)

## Built on by (most cited first, 7 of 7)

- [From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future](https://mlsanity.com/paper/2408.02479/) (2024)
- [The Few-shot Dilemma: Over-prompting Large Language Models](https://mlsanity.com/paper/2509.13196/) (2025)
- [ReqInOne: A Large Language Model-Based Agent for Software Requirements Specification Generation](https://mlsanity.com/paper/2508.09648/) (2025)
- [Synthline: A Product Line Approach for Synthetic Requirements Engineering Data Generation using Large Language Models](https://mlsanity.com/paper/2505.03265/) (2025)
- [Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking](https://mlsanity.com/paper/2610.10628/) (2026)
- [Multi-Sample Prompting and Actor-Critic Prompt Optimization for Diverse Synthetic Data Generation](https://mlsanity.com/paper/2506.21138/) (2025)
- [How Well Can AI Generate Backlogs from App Mockups?](https://mlsanity.com/paper/2607.22902/) (2026)

## Abstract (arXiv)

Recently, Large Language Models like ChatGPT have demonstrated remarkable proficiency in various Natural Language Processing tasks. Their application in Requirements Engineering, especially in requirements classification, has gained increasing interest. This paper reports an extensive empirical evaluation of two ChatGPT models, specifically gpt-3.5-turbo, and gpt-4 in both zero-shot and few-shot settings for requirements classification. The question arises as to how these models compare to traditional classification methods, specifically Support Vector Machine and Long Short-Term Memory. Based on five different datasets, our results show that there is no single best technique for all types of requirement classes. Interestingly, the few-shot setting has been found to be beneficial primarily in scenarios where zero-shot results are significantly low.