From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions
Submission Type: Regular Long Paper
Submission Track: NLP Applications
Submission Track 2: Theme Track: Large Language Models and the Future of NLP
Keywords: applications, code generation, electronics, language models
TL;DR: Demonstrates that language models like GPT-4 can design electronic circuits from high-level textual descriptions, achieving high success rates in generating 25 benchmark devices, while functioning as a design assistant for more complex devices.
Abstract: In this work, we show that contemporary language models have a previously unknown skill -- the capacity for electronic circuit design from high-level textual descriptions, akin to code generation. We introduce two benchmarks: PINS100, assessing model knowledge of electrical components, and MICRO25, evaluating a model's capability to design common microcontroller circuits and code in the Arduino ecosystem that involve input, output, sensors, motors, protocols, and logic -- with models such as GPT-4 and Claude-V1 achieving between 60% to 96% Pass@1 on generating full devices. We include six case studies of using language models as a design assistant for moderately complex devices, such as a radiation-powered random number generator, an emoji keyboard, a visible spectrometer, and several assistive devices, while offering a qualitative analysis performance, outlining evaluation challenges, and suggesting areas of development to improve complex circuit design and practical utility. With this work, we aim to spur research at the juncture of natural language processing and electronic design.
Submission Number: 837
Loading