HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ping, Heng, Li, Shixuan, Zhang, Peiyu, Cheng, Anzhe, Duan, Shukai, Kanakaris, Nikos, Xiao, Xiongye, Yang, Wei, Nazarian, Shahin, Irimia, Andrei, Bogdan, Paul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913748511358976
author Ping, Heng
Li, Shixuan
Zhang, Peiyu
Cheng, Anzhe
Duan, Shukai
Kanakaris, Nikos
Xiao, Xiongye
Yang, Wei
Nazarian, Shahin
Irimia, Andrei
Bogdan, Paul
author_facet Ping, Heng
Li, Shixuan
Zhang, Peiyu
Cheng, Anzhe
Duan, Shukai
Kanakaris, Nikos
Xiao, Xiongye
Yang, Wei
Nazarian, Shahin
Irimia, Andrei
Bogdan, Paul
contents Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, when applied to hardware description languages (HDL), these models exhibit significant limitations due to data scarcity, resulting in hallucinations and incorrect code generation. To address these challenges, we propose HDLCoRe, a training-free framework that enhances LLMs' HDL generation capabilities through prompt engineering techniques and retrieval-augmented generation (RAG). Our approach consists of two main components: (1) an HDL-aware Chain-of-Thought (CoT) prompting technique with self-verification that classifies tasks by complexity and type, incorporates domain-specific knowledge, and guides LLMs through step-by-step self-simulation for error correction; and (2) a two-stage heterogeneous RAG system that addresses formatting inconsistencies through key component extraction and efficiently retrieves relevant HDL examples through sequential filtering and re-ranking. HDLCoRe eliminates the need for model fine-tuning while substantially improving LLMs' HDL generation capabilities. Experimental results demonstrate that our framework achieves superior performance on the RTLLM2.0 benchmark, significantly reducing hallucinations and improving both syntactic and functional correctness.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16528
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL
Ping, Heng
Li, Shixuan
Zhang, Peiyu
Cheng, Anzhe
Duan, Shukai
Kanakaris, Nikos
Xiao, Xiongye
Yang, Wei
Nazarian, Shahin
Irimia, Andrei
Bogdan, Paul
Computation and Language
Artificial Intelligence
Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, when applied to hardware description languages (HDL), these models exhibit significant limitations due to data scarcity, resulting in hallucinations and incorrect code generation. To address these challenges, we propose HDLCoRe, a training-free framework that enhances LLMs' HDL generation capabilities through prompt engineering techniques and retrieval-augmented generation (RAG). Our approach consists of two main components: (1) an HDL-aware Chain-of-Thought (CoT) prompting technique with self-verification that classifies tasks by complexity and type, incorporates domain-specific knowledge, and guides LLMs through step-by-step self-simulation for error correction; and (2) a two-stage heterogeneous RAG system that addresses formatting inconsistencies through key component extraction and efficiently retrieves relevant HDL examples through sequential filtering and re-ranking. HDLCoRe eliminates the need for model fine-tuning while substantially improving LLMs' HDL generation capabilities. Experimental results demonstrate that our framework achieves superior performance on the RTLLM2.0 benchmark, significantly reducing hallucinations and improving both syntactic and functional correctness.
title HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.16528