Execution-Anchored Hallucination Calibration Reranking for Verilog Code Generation

2026-08-24

AI Summary

研究解决了低资源硬件描述语言Verilog代码生成问题，提出EAHC框架，结合执行信号和推理信号以优化多候选重排序。

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, yet their performance degrades significantly on low-resource Hardware Description Languages such as Verilog. While multi-candidate sampling improves the likelihood of generating correct solutions, au-tomatically selecting the optimal candidate remains an open challenge. Through a systematic empirical study across nine models and two benchmarks, we identify two critical limitations:(1) existing execution-based reranking methods, which rely on testbench pass/fail outcomes, exhibit poor domain transferability due to low-quality generated testbenches; and (2) LLM-as-a-Judge suffers from reasoning hallucination, producing incon-sistent judgments for execution-equivalent code. These findings reveal two signal types with orthogonal errors: execution signals(deterministic but testbench coverage limited)and reasoning signals (semantically rich but hallucination-prone). Their orthog-onality suggests combining the two signals, yet in our experiments letting the reasoner directly observe execution results merely anchors its judgments on test outcomes; we therefore acquire the two signals independently and fuse them only at the decision stage. Based on these insights, we propose EAHC, an Execution-Anchored Hallucination Calibration reranking framework that anchors reasoning judgments to execution behavior so that execution-equivalent candidates receive consistent scores, which implements a dual-channel architecture: EAHC-R, a 4B reasoning discriminator; and EAHC-T, a testbench generator leveraging RAG for execution verification.

Problem

• Large Language Models
• Verilog Code Generation
• Reranking
• Execution-based Methods
• Reasoning Hallucination

Innovation

• Execution-Anchored Hallucination Calibration
• dual-channel architecture
• reasoning hallucination
• execution signals
• testbench generator