I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation
It addresses the problem of improving LLM reliability in real-world applications by balancing performance gains with user burden, though it is incremental as it focuses on a specific case study.
This study investigates whether large language models (LLMs) can proactively ask for user support in text-to-SQL generation, finding that without external feedback, many LLMs struggle to recognize when they need help.
This study explores the proactive ability of LLMs to seek user support. We propose metrics to evaluate the trade-off between performance improvements and user burden, and investigate whether LLMs can determine when to request help under varying information availability. Our experiments show that without external feedback, many LLMs struggle to recognize their need for user support. The findings highlight the importance of external signals and provide insights for future research on improving support-seeking strategies. Source code: https://github.com/appier-research/i-need-help