# Are Prompts All You Need? Evaluating Prompt-Based Large Language Models (LLM)s for Software Requirements Classification

arXiv: https://arxiv.org/abs/2509.13868 · HTML: https://mlsanity.com/paper/2509.13868/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2025.

## Built on by (most cited first, 3 of 3)

- [Light over Heavy: Automated Performance Requirements Quantification with Linguistic Inducement](https://mlsanity.com/paper/2511.03421/) (2025)
- [Conjecture and Inquiry: Quantifying Software Performance Requirements via Interactive Retrieval-Augmented Preference Elicitation](https://mlsanity.com/paper/2604.21380/) (2026)
- [A Framework for Identifying, Categorizing, and Explaining Bias in AI-Generated Code](https://mlsanity.com/paper/2609.30642/) (2026)

## Abstract (arXiv)

Requirements classification assigns natural language requirements to predefined classes, such as functional and non functional. Accurate classification reduces risk and improves software quality. Most existing models rely on supervised learning, which needs large labeled data that are costly, slow to create, and domain dependent; they also generalize poorly and often require retraining for each task. This study tests whether prompt based large language models can reduce data needs. We benchmark several models and prompting styles (zero shot, few shot, persona, and chain of thought) across multiple tasks on two English datasets, PROMISE and SecReq. For each task we compare model prompt configurations and then compare the best LLM setups with a strong fine tuned transformer baseline. Results show that prompt based LLMs, especially with few shot prompts, can match or exceed the baseline. Adding a persona, or persona plus chain of thought, can yield further gains. We conclude that prompt based LLMs are a practical and scalable option that reduces dependence on large annotations and can improve generalizability across tasks.