CorrectBench: Automatic Testbench Generation with Functional Self-Correction using LLMs for HDL Design

• URL: http://arxiv.org/abs/2411.08510v1
• Date: Wed, 13 Nov 2024 10:45:19 GMT
• Title: CorrectBench: Automatic Testbench Generation with Functional Self-Correction using LLMs for HDL Design
• Authors: Ruidi Qiu, Grace Li Zhang, Rolf Drechsler, Ulf Schlichtmann, Bing Li,
• Abstract summary: We propose CorrectBench, an automatic testbench generation framework with functional self-validation and self-correction. The proposed approach can validate the correctness of the generated testbenches with a success rate of 88.85%. Our work's performance is 62.18% higher than previous work in sequential tasks and almost 5 times the pass ratio of the direct method.
• Score: 6.414167153186868
• License:
• Abstract: Functional simulation is an essential step in digital hardware design. Recently, there has been a growing interest in leveraging Large Language Models (LLMs) for hardware testbench generation tasks. However, the inherent instability associated with LLMs often leads to functional errors in the generated testbenches. Previous methods do not incorporate automatic functional correction mechanisms without human intervention and still suffer from low success rates, especially for sequential tasks. To address this issue, we propose CorrectBench, an automatic testbench generation framework with functional self-validation and self-correction. Utilizing only the RTL specification in natural language, the proposed approach can validate the correctness of the generated testbenches with a success rate of 88.85%. Furthermore, the proposed LLM-based corrector employs bug information obtained during the self-validation process to perform functional self-correction on the generated testbenches. The comparative analysis demonstrates that our method achieves a pass ratio of 70.13% across all evaluated tasks, compared with the previous LLM-based testbench generation framework's 52.18% and a direct LLM-based generation method's 33.33%. Specifically in sequential circuits, our work's performance is 62.18% higher than previous work in sequential tasks and almost 5 times the pass ratio of the direct method. The codes and experimental results are open-sourced at the link: https://github.com/AutoBench/CorrectBench

Related papers

• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis [50.020850767257095]
  We propose ProofAug, a novel theorem proving method that enjoys superior sample efficiency. Our method is validated on the miniF2F-test benchmark using the open-source deepseek-math-7b-base model and the Isabelle proof assistant.
  arXiv  Detail & Related papers  (2025-01-30T12:37:06Z)
• Planning-Driven Programming: A Large Language Model Programming Workflow [8.827173113748701]
  Large language models (LLMs) are strong performers in code generation. Recent research suggests continuous program refinements through visible tests to improve code generation accuracy in LLMs. We propose an LLM programming workflow (LPW) designed to improve both initial code generation and subsequent refinements.
  arXiv  Detail & Related papers  (2024-11-21T08:31:06Z)
• AutoBench: Automatic Testbench Generation and Evaluation Using LLMs for HDL Design [6.414167153186868]
  Testbenches constitute the cornerstone of simulation-based hardware verification. Large Language Models (LLMs) have demonstrated their potential in automating the circuit design flow. We introduce AutoBench, the first LLM-based testbench generator for digital circuit design.
  arXiv  Detail & Related papers  (2024-07-04T12:33:56Z)
• BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions [72.56339136017759]
  We introduce BigCodeBench, a benchmark that challenges Large Language Models (LLMs) to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. Our evaluation shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. We propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information.
  arXiv  Detail & Related papers  (2024-06-22T15:52:04Z)
• Revisiting Unnaturalness for Automated Program Repair in the Era of Large Language Models [9.454475517867817]
  We propose a patch-naturalness measurement, entropy-delta, to improve the efficiency of template-based repair techniques. Our proposed method can rank correct patches more effectively than state-of-the-art machine learning tools.
  arXiv  Detail & Related papers  (2024-04-23T17:12:45Z)
• GRATH: Gradual Self-Truthifying for Large Language Models [63.502835648056305]
  GRAdual self-truTHifying (GRATH) is a novel post-processing method to enhance truthfulness of large language models (LLMs) GRATH iteratively refines truthfulness data and updates the model, leading to a gradual improvement in model truthfulness in a self-supervised manner. GRATH achieves state-of-the-art performance on TruthfulQA, with MC1 accuracy of 54.71% and MC2 accuracy of 69.10%, which even surpass those on 70B-LLMs.
  arXiv  Detail & Related papers  (2024-01-22T19:00:08Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Factcheck-Bench: Fine-Grained Evaluation Benchmark for Automatic Fact-checkers [121.53749383203792]
  We present a holistic end-to-end solution for annotating the factuality of large language models (LLMs)-generated responses. We construct an open-domain document-level factuality benchmark in three-level granularity: claim, sentence and document. Preliminary experiments show that FacTool, FactScore and Perplexity are struggling to identify false claims.
  arXiv  Detail & Related papers  (2023-11-15T14:41:57Z)
• An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation [3.9762912548964864]
  This paper presents a large-scale empirical evaluation on the effectiveness of Large Language Models for automated unit test generation. We implement our approach in TestPilot, a test generation tool for JavaScript that automatically generates unit tests for all API functions in an npm package. We find that 92.8% of TestPilot's generated tests have no more than 50% similarity with existing tests.
  arXiv  Detail & Related papers  (2023-02-13T17:13:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.