QiMeng-CRUX: Narrowing the Gap between Natural Language and Verilog via Core Refined Understanding eXpression

• URL: http://arxiv.org/abs/2511.20099v2
• Date: Wed, 26 Nov 2025 10:46:28 GMT
• Title: QiMeng-CRUX: Narrowing the Gap between Natural Language and Verilog via Core Refined Understanding eXpression
• Authors: Lei Huang, Rui Zhang, Jiaming Guo, Yang Zhang, Di Huang, Shuyao Cheng, Pengwei Jin, Chongxiao Li, Zidong Du, Xing Hu, Qi Guo, Yunji Chen,
• Abstract summary: Large language models (LLMs) have shown promising capabilities in hardware description language (HDL) generation.<n>Existing approaches often rely on free-form natural language descriptions that are often ambiguous, redundant, and unstructured.<n>We treat hardware code generation as a complex transformation from an open-ended natural language space to a domain-specific, highly constrained target space.<n>We introduce Core Refined Understanding eXpression (CRUX), a structured intermediate space that captures the essential semantics of user intent while organizing the expression for precise Verilog code generation.
• Score: 48.84841760215598
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) have shown promising capabilities in hardware description language (HDL) generation. However, existing approaches often rely on free-form natural language descriptions that are often ambiguous, redundant, and unstructured, which poses significant challenges for downstream Verilog code generation. We treat hardware code generation as a complex transformation from an open-ended natural language space to a domain-specific, highly constrained target space. To bridge this gap, we introduce Core Refined Understanding eXpression (CRUX), a structured intermediate space that captures the essential semantics of user intent while organizing the expression for precise Verilog code generation. We further design a two-stage training framework, comprising Joint Expression Modeling and Dual-Space Optimization, to enhance the quality of both CRUX and Verilog code. Experiments across multiple Verilog generation benchmarks demonstrate that our model, CRUX-V, achieves state-of-the-art performance among general models, particularly under challenging design tasks. Furthermore, the CRUX space proves transferable and beneficial when used as input prompts for other code models, highlighting its effectiveness in narrowing the gap between free-form natural language descriptions and precise Verilog generation.

Related papers

• NAG: A Unified Native Architecture for Encoder-free Text-Graph Modeling in Language Models [33.49410203951687]
  We argue this approach is suboptimal for text-graphs.<n>NAG (Native Architecture for Graphs) is a unified framework that internalizes graph processing within the Language Models.<n>NAG achieves robust graph comprehension without the overhead of external encoders.
  arXiv  Detail & Related papers  (2026-01-30T07:22:11Z)
• VeriGRAG: Enhancing LLM-Based Verilog Code Generation with Structure-Aware Soft Prompts [4.227182480042518]
  We propose a novel framework that extracts structural graph embeddings from Verilog code using graph neural networks (GNNs)<n>A multimodal retriever then selects the graph embeddings most relevant to the given generation task.<n>Experiments demonstrate that VeriGRAG substantially improves the correctness of Verilog code generation.
  arXiv  Detail & Related papers  (2025-09-27T10:23:36Z)
• ProtocolLLM: RTL Benchmark for SystemVerilog Generation of Communication Protocols [45.66401695351214]
  We introduce ProtocolLLM, the first benchmark suite specifically targeting widely used SystemVerilog protocols.<n>We observe that most of the models fail to generate SystemVerilog code for communication protocols that follow timing constrains.
  arXiv  Detail & Related papers  (2025-06-09T17:10:47Z)
• DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model [13.532046953850902]
  We present DeepRTL, a unified representation model that excels in both Verilog understanding and generation.<n>Based on CodeT5+, DeepRTL is fine-tuned on a comprehensive dataset that aligns Verilog code with rich, multi-level natural language descriptions.<n>We introduce the first benchmark for Verilog understanding and take the initiative to apply embedding similarity and GPT Score to evaluate the models' understanding capabilities.
  arXiv  Detail & Related papers  (2025-02-20T11:07:55Z)
• Natural language is not enough: Benchmarking multi-modal generative AI for Verilog generation [37.309663295844835]
  We introduce an open-source benchmark for multi-modal generative models tailored for Verilog synthesis from visual-linguistic inputs. We also introduce an open-source visual and natural language Verilog query language framework. Our results demonstrate a significant improvement in the multi-modal generated Verilog compared to queries based solely on natural language.
  arXiv  Detail & Related papers  (2024-07-11T13:10:09Z)
• Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs [57.27982780697922]
  Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process. This paper introduces Lexical Unit Decoding, a novel decoding methodology implemented in a data-driven manner.
  arXiv  Detail & Related papers  (2024-05-24T04:35:13Z)
• CodeGRAG: Bridging the Gap between Natural Language and Programming Language via Graphical Retrieval Augmented Generation [58.84212778960507]
  CodeGRAG builds the graphical view of code blocks based on the control flow and data flow of them to better interpret the programming domain knowledge.<n>CodeGRAG significantly improves the code generation ability of LLMs and can even offer performance gain for cross-lingual code generation.
  arXiv  Detail & Related papers  (2024-05-03T02:48:55Z)
• AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone Detection [69.79627042058048]
  AdaCCD is a novel cross-lingual adaptation method that can detect cloned codes in a new language without annotations in that language. We evaluate the cross-lingual adaptation results of AdaCCD by constructing a multilingual code clone detection benchmark consisting of 5 programming languages.
  arXiv  Detail & Related papers  (2023-11-13T12:20:48Z)
• The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding [65.34601470417967]
  We describe a hybrid architecture for dialogue response generation that combines the strengths of neural language modeling and rule-based generation. Our experiments show that this system outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.
  arXiv  Detail & Related papers  (2022-09-16T09:00:49Z)
• Logical Natural Language Generation from Open-Domain Tables [107.04385677577862]
  We propose a new task where a model is tasked with generating natural language statements that can be emphlogically entailed by the facts. To facilitate the study of the proposed logical NLG problem, we use the existing TabFact dataset citechen 2019tabfact featured with a wide range of logical/symbolic inferences. The new task poses challenges to the existing monotonic generation frameworks due to the mismatch between sequence order and logical order.
  arXiv  Detail & Related papers  (2020-04-22T06:03:10Z)

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.