Mockingbird: How does LLM perform in general machine learning tasks?
This work addresses the potential of LLMs for general machine learning applications, but it is incremental as it shows limitations compared to existing methods.
The authors tackled the problem of adapting large language models (LLMs) to general machine learning tasks by proposing the Mockingbird framework, which uses role-playing and self-reflection, and found it achieves acceptable results but does not outperform domain-specific documents or human expert feedback.
Large language models (LLMs) are now being used with increasing frequency as chat bots, tasked with the summarizing information or generating text and code in accordance with user instructions. The rapid increase in reasoning capabilities and inference speed of LLMs has revealed their remarkable potential for applications extending beyond the domain of chat bots to general machine learning tasks. This work is conducted out of the curiosity about such potential. In this work, we propose a framework Mockingbird to adapt LLMs to general machine learning tasks and evaluate its performance and scalability on several general machine learning tasks. The core concept of this framework is instructing LLMs to role-play functions and reflect on its mistakes to improve itself. Our evaluation and analysis result shows that LLM-driven machine learning methods, such as Mockingbird, can achieve acceptable results on common machine learning tasks; however, solely reflecting on its own currently cannot outperform the effect of domain-specific documents and feedback from human experts.