Generative Information Systems Are Great If You Can Read
Adam Roegiest, Zuzana Pinkosova
Abstract
Generative models, especially in information systems like ChatGPT and Bing Chat, have become increasingly integral to our daily lives. Their significance lies in their potential to revolutionize how we access, process, and generate information [44]. However, a gap exists in ensuring these systems are accessible to all, especially considering the literacy challenges faced by a significant portion of the population in (but not limited to) English-speaking countries. This paper aims to investigate the “readability’’ of generative information systems and their accessibility barriers, particularly for those with literacy challenges. Using popular instruction fine-tuning datasets, we found that this training data could produce systems that generate at a college level, potentially excluding a large demographic. Our research methods involved analyzing the responses of popular Large Language Models (LLMs) and examining potential biases in how they can be trained. The key message is the urgent need for inclusivity in systems incorporating generative models, such as those studied by the Information Retrieval (IR) community. Our findings indicate that current generative systems might not be accessible to individuals with cognitive and literacy challenges, emphasizing the importance of ensuring that advancements in this field benefit everyone. By situating our research within the sphere of information seeking and retrieval, we underscore the essential role of these technologies in augmenting accessibility and efficiency of information access, thereby broadening their reach and enhancing user engagement.