Empirical Evaluation of ChatGPT on Requirements Information Retrieval Under Zero-Shot Setting
This provides preliminary evidence for improving requirements retrieval tools using large language models, but it is incremental as it applies an existing model to a new domain.
The paper evaluated ChatGPT's performance on requirements information retrieval tasks under a zero-shot setting, finding it has high recall for retrieving relevant information but low precision for specific details.
Recently, various illustrative examples have shown the impressive ability of generative large language models (LLMs) to perform NLP related tasks. ChatGPT undoubtedly is the most representative model. We empirically evaluate ChatGPT's performance on requirements information retrieval (IR) tasks to derive insights into designing or developing more effective requirements retrieval methods or tools based on generative LLMs. We design an evaluation framework considering four different combinations of two popular IR tasks and two common artifact types. Under zero-shot setting, evaluation results reveal ChatGPT's promising ability to retrieve requirements relevant information (high recall) and limited ability to retrieve more specific requirements information (low precision). Our evaluation of ChatGPT on requirements IR under zero-shot setting provides preliminary evidence for designing or developing more effective requirements IR methods or tools based on LLMs.