E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models
This addresses the challenge of making LLMs more accessible and reliable for users by systematically assessing their robustness to common input errors, though it is incremental as it focuses on evaluation rather than solving the underlying issue.
The paper tackles the problem of large language models (LLMs) being sensitive to prompt variations, which hinders their ease-of-use, by proposing E-Bench to evaluate stability against perturbations like synonyms and typos; results show that while larger models improve ease-of-use, they still fall short of being sufficiently user-friendly.
Most large language models (LLMs) are sensitive to prompts, and another synonymous expression or a typo may lead to unexpected results for the model. Composing an optimal prompt for a specific demand lacks theoretical support and relies entirely on human experimentation, which poses a considerable obstacle to popularizing generative artificial intelligence. However, there is no systematic analysis of the stability of LLMs in resisting prompt perturbations in real-world scenarios. In this work, we propose to evaluate the ease-of-use of LLMs and construct E-Bench, simulating the actual situation of human use from synonymous perturbation (including paraphrasing, simplification, and colloquialism) and typographical perturbation (such as typing). On this basis, we also discuss the combination of these two types of perturbation and analyze the main reasons for performance degradation. Experimental results indicate that with the increase of model size, although the ease-of-use are significantly improved, there is still a long way to go to build a sufficiently user-friendly model.