Forgetful Large Language Models: Lessons Learned from Using LLMs in Robot Programming
DOI:
https://doi.org/10.1609/aaaiss.v2i1.27721Keywords:
Large Language Model, Robot Programming, Code Generation, Prompt EngineeringAbstract
Large language models offer new ways of empowering people to program robot applications-namely, code generation via prompting. However, the code generated by LLMs is susceptible to errors. This work reports a preliminary exploration that empirically characterizes common errors produced by LLMs in robot programming. We categorize these errors into two phases: interpretation and execution. In this work, we focus on errors in execution and observe that they are caused by LLMs being “forgetful” of key information provided in user prompts. Based on this observation, we propose prompt engineering tactics designed to reduce errors in execution. We then demonstrate the effectiveness of these tactics with three language models: ChatGPT, Bard, and LLaMA-2. Finally, we discuss lessons learned from using LLMs in robot programming and call for the benchmarking of LLM-powered end-user development of robot applications.Downloads
Published
2024-01-22
Issue
Section
Unifying Representations for Robot Application Development