paper-with-me

Papers

VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination

2025-03-17 · Zeng Wang, Minghao Shao, Jitendra Bhandari, Likhitha Mankali, Ramesh Karri, Ozgur Sinanoglu, Muhammad Shafique, Johann Knechtel

Large Language Models (LLMs) have revolutionized code generation, achieving exceptional results on various established benchmarking frameworks. However, concerns about data contamination - where benchmark data inadvertently leaks into pre-training or fine-tuning datasets - raise questions about the validity of these evaluations. While this issue is known, limiting the industrial adoption of LLM-driven software engineering, hardware coding has received little to no attention regarding these risks. For the first time, we analyze state-of-the-art (SOTA) evaluation frameworks for Verilog code generation (VerilogEval and RTLLM), using established methods for contamination detection (CCD and Min-K% Prob). We cover SOTA commercial and open-source LLMs (CodeGen2.5, Minitron 4b, Mistral 7b, phi-4 mini, LLaMA-{1,2,3.1}, GPT-{2,3.5,4o}, Deepseek-Coder, and CodeQwen 1.5), in baseline and fine-tuned models (RTLCoder and Verigen). Our study confirms that data contamination is a critical concern. We explore mitigations and the resulting trade-offs for code quality vs fairness (i.e., reducing contamination toward unbiased benchmarking).

📄 PDF Abstract BibTeX arXiv:2503.13572

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingCode GenerationFairness

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

VeriLeaky: Navigating IP Protection vs Utility in Fine-Tuning for LLM-Driven Verilog Coding

2025-03-17 · Zeng Wang, Minghao Shao, Mohammed Nabeel, Prithwish Basu Roy 외

Large language models (LLMs) offer significant potential for coding, yet fine-tuning (FT) with curated data is essential for niche languages like Verilog. Using proprietary intellectual property (IP) for FT presents a se…

Speculative Decoding for Verilog: Speed and Quality, All in One

2025-03-18 · Changran Xu, Yi Liu, Yunhao Zhou, Shan Huang 외

The rapid advancement of large language models (LLMs) has revolutionized code generation tasks across various programming languages. However, the unique characteristics of programming languages, particularly those like V…

AllCode Generation

Verilog-Evolve: Feedback-Driven and Skill-Evolving Verilog Generation

2026-05-26 · Zehua Pei, Hui-Ling Zhen, Yu Zhang, Sinno Jialin Pan 외 arxiv

Large language models (LLMs) have improved Verilog generation from natural-language specifications, but most pipelines still treat generation as isolated sampling followed by functional checking. This is insufficient for…

VerilogCoder: Autonomous Verilog Coding Agents with Graph-based Planning and Abstract Syntax Tree (AST)-based Waveform Tracing Tool

2024-08-15 · Chia-Tung Ho, Haoxing Ren, Brucek Khailany

Due to the growing complexity of modern Integrated Circuits (ICs), automating hardware design can prevent a significant amount of human error from the engineering process and result in less errors. Verilog is a popular h…

Code Generation

CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair

2024-09-19 · Mingjie Liu, Yun-Da Tsai, Wenfei Zhou, Haoxing Ren

Despite the significant progress made in code generation with large language models, challenges persist, especially with hardware description languages such as Verilog. This paper first presents an analysis of fine-tuned…

Code GenerationCode RepairSynthetic Data Generation