The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions

Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

Submission Type: Regular Long Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Keywords: Large language models, Real-world NLP applications, User-GPT interaction analysis

Abstract: Recent progress in Large Language Models (LLMs) has produced models that exhibit remarkable performance across a variety of NLP tasks. However, it remains unclear whether the existing focus of NLP research accurately captures the genuine requirements of human users. This paper provides a comprehensive analysis of the divergence between academic research in NLP and the needs of real-world NLP applications via a large-scale collection of user-GPT conversations. We analyze a large-scale collection of real user queries to GPT. We compare these queries against existing NLP benchmark tasks and identify a significant gap between the tasks that users frequently request from LLMs and the tasks that are commonly studied in academic research. For example, we find that tasks such as "design" and "planning" are prevalent in user interactions but largely neglected or different from traditional NLP benchmarks. We investigate these overlooked tasks, dissect the practical challenges, and provide insights toward a roadmap to make LLMs better aligned with user needs.

Submission Number: 4451