ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Model

TL;DR

ChipExpert is an open-source, specialized large language model tailored for integrated circuit design, trained with custom datasets and enhanced with retrieval-augmented generation to improve expertise and reduce hallucinations.

Contribution

The paper introduces ChipExpert, the first open-source LLM specifically designed for IC design, including its training process, alignment, and a new benchmark for evaluation.

Findings

High performance on IC design question-answering tasks

Effective reduction of hallucinations via retrieval-augmented generation

Demonstrates expertise across multiple IC design sub-domains

Abstract

The field of integrated circuit (IC) design is highly specialized, presenting significant barriers to entry and research and development challenges. Although large language models (LLMs) have achieved remarkable success in various domains, existing LLMs often fail to meet the specific needs of students, engineers, and researchers. Consequently, the potential of LLMs in the IC design domain remains largely unexplored. To address these issues, we introduce ChipExpert, the first open-source, instructional LLM specifically tailored for the IC design field. ChipExpert is trained on one of the current best open-source base model (Llama-3 8B). The entire training process encompasses several key stages, including data preparation, continue pre-training, instruction-guided supervised fine-tuning, preference alignment, and evaluation. In the data preparation stage, we construct multiple high-quality custom datasets through manual selection and data synthesis techniques. In the subsequent two stages, ChipExpert acquires a vast amount of IC design knowledge and learns how to respond to user queries professionally. ChipExpert also undergoes an alignment phase, using Direct Preference Optimization, to achieve a high standard of ethical performance. Finally, to mitigate the hallucinations of ChipExpert, we have developed a Retrieval-Augmented Generation (RAG) system, based on the IC design knowledge base. We also released the first IC design benchmark ChipICD-Bench, to evaluate the capabilities of LLMs across multiple IC design sub-domains. Through comprehensive experiments conducted on this benchmark, ChipExpert demonstrated a high level of expertise in IC design knowledge Question-and-Answer tasks.