Pith. sign in

REVIEW 6 cited by

OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.16237 v2 pith:CB72BBBG submitted 2024-07-23 cs.AR cs.AIcs.LG

classification cs.ARcs.AIcs.LG
keywords codeopen-sourceorigenself-reflectionaugmentationcapabilitiesgenerationgpt-4
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent studies have demonstrated the significant potential of Large Language Models (LLMs) in generating Register Transfer Level (RTL) code, with notable advancements showcased by commercial models such as GPT-4 and Claude3-Opus. However, these proprietary LLMs often raise concerns regarding privacy and security. While open-source LLMs offer solutions to these concerns, they typically underperform commercial models in RTL code generation tasks, primarily due to the scarcity of high-quality open-source RTL datasets. To address this challenge, we introduce OriGen , a fully open-source framework that incorporates self-reflection capabilities and a novel dataset augmentation methodology for generating high-quality, large-scale RTL code. Our approach employs a code-tocode augmentation technique to enhance the quality of open-source RTL code datasets. Furthermore, OriGen can rectify syntactic errors through a self-reflection process that leverages compiler feedback. Experimental results demonstrate that OriGen significantly outperforms other open-source alternatives in RTL code generation. It surpasses the previous best-performing open-source LLM by 12.8% and even exceeds GPT-4 Turbo in the pass@1 metric on the VerilogEval-Human benchmark. Moreover, OriGen exhibits superior capabilities in self-reflection and error correction, outperforming GPT-4 by 19.9% on a benchmark designed to evaluate self-reflection capabilities.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AutoVeriFix: Automatically Correcting Errors and Enhancing Functional Correctness in LLM-Generated Verilog Code

    cs.AR 2025-09 conditional novelty 6.0 of 10

    AutoVeriFix improves LLM-generated Verilog functional correctness by generating a high-level Python reference model, deriving a high-coverage testbench, and iteratively fixing Verilog simulation mismatches.

  2. Iceberg: Enhancing HLS Modeling with Synthetic Data

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Pretraining on LLM-generated HLS programs plus GNN weak labels reduces few-shot latency prediction error by 86% on six real-world applications.

  3. DeepRTL2: A Versatile Model for RTL-Related Tasks

    cs.AR 2025-05 reject novelty 6.0 of 10

    DeepRTL2 claims state-of-the-art results across RTL generation, understanding, code search, equivalence checking, and performance prediction, but the evidence is weakened by benchmark construction issues and a contrad...

  4. ChipVerilog: A Large-Scale OpenCores-Derived Benchmark for LLM-Based Verilog RTL Generation

    cs.AR 2026-07 conditional novelty 5.0 of 10

    On 64 large OpenCores-derived Verilog tasks, top LLMs reach 23.6% functional pass@1, 37.5% pass@5, and 0% on designs with two or more submodules, showing hierarchical RTL generation remains unsolved.

  5. DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs

    cs.PL 2025-07 conditional novelty 5.0 of 10

    DecoRTL combines token-class-aware temperature adjustment with contrastive top-K reranking to improve synthesizability and functional correctness of LLM-generated Verilog.

  6. VerilogDB: The Largest, Highest-Quality Dataset with a Preprocessing Framework for LLM-based RTL Generation

    cs.AR 2025-07 conditional novelty 4.0 of 10

    A new pipeline and dataset of 20,392 synthesis-checked Verilog modules for LLM fine-tuning is presented, claimed to be the largest high-quality dataset of its kind.

Pith tools