Execution-Anchored Hallucination Calibration Reranking for Verilog Code Generation

• URL: http://arxiv.org/abs/2608.22938v1
• Date: Mon, 24 Aug 2026 08:11:43 GMT
• Title: Execution-Anchored Hallucination Calibration Reranking for Verilog Code Generation
• Abstract summary: Large Language Models (LLMs) have demonstrated remarkable capabilities in code generation, yet their performance degrades significantly on low-resource languages.<n>We propose EAHC, an Execution-Anchored Hallucination reranking framework that anchors reasoning judgments to execution behavior.
• Score: 19.257000641887828
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Coverage-Driven RTL Assertion Generation with Formal Exploration and Neuro-Symbolic Refinement [3.5085139194562456]
  NeuroAssertion is a coverage-driven assertion generation framework.<n>It combines formal trace generation, syntax-guided synthesis, and agent-inspired refinement.<n>It delivers around 2X more assertions and about 2X higher mutation coverage than traditional assertion mining methods.
  arXiv  Detail & Related papers  (2026-08-19T03:14:14Z)
• Speculative Refinement: A Hybrid Autoregressive Diffusion Decoding Strategy and Its Behavior Across Benchmarks [1.9800951131982487]
  We use Speculative Refinement (SpecRef) to warm-start a masked diffusion language model from an AR draft.<n>We evaluate SpecRef across six benchmarks (HumanEval, MBPP, GSM8K, BBH, ARC-Challenge, HellaSwag) with three distinct evaluation protocols.<n>These observations apply to any multi-stage or non-autoregressive generation pipeline and point toward more diagnostic evaluation practices.
  arXiv  Detail & Related papers  (2026-06-25T18:52:24Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• FeedbackLLM: Metadata driven Multi-Agentic Language Agnostic Test Case Generator with Evolving prompt and Coverage Feedback [0.0]
  Traditional approaches to test case generation often involve manual effort and incur significant computational overhead.<n>We propose FeedbackLLM, a novel automated language-agnostic test case generation framework based on tightly coupled two-stage approach.<n>The performance of the proposed architecture is evaluated on the standard benchmark programs related to C and Python programs.
  arXiv  Detail & Related papers  (2026-05-02T05:43:29Z)
• DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode [56.14374797825548]
  We introduce LLM-based pseudocode execution, which grounds prediction on more error-resilient pseudocode.<n>We propose DuET, a dual-execution framework that combines both approaches by functional majority voting.<n>On LiveCodeBench, DuET achieves the state-of-the-art performance, improving Pass@1 by 13.6 pp.
  arXiv  Detail & Related papers  (2026-04-13T14:18:58Z)
• Scaling Agentic Verifier for Competitive Coding [66.11758166379092]
  Large language models (LLMs) have demonstrated strong coding capabilities but still struggle to solve competitive programming problems correctly in a single attempt.<n>Execution-based re-ranking offers a promising test-time scaling strategy, yet existing methods are constrained by either difficult test case generation or inefficient random input sampling.<n>We propose Agentic Verifier, an execution-based agent that actively reasons about program behaviors and searches for highly discriminative test inputs.
  arXiv  Detail & Related papers  (2026-02-04T06:30:40Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding [4.220190655754022]
  Large Language Models (LLMs) have achieved remarkable performance across diverse tasks, yet their susceptibility to generating incorrect content during inference remains a critical unsolved challenge.<n>We propose Feedback-Triggered Regeneration (FTR), a novel framework that synergizes user feedback with enhanced decoding dynamics.<n>Specifically, FTR activates response regeneration only upon receiving negative user feedback, thereby circumventing error propagation from faulty self-assessment while preserving originally correct outputs.
  arXiv  Detail & Related papers  (2025-09-09T12:43:28Z)
• Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling [51.38330727868982]
  We show how action chunking impacts the divergence between a learner and a demonstrator.<n>We propose Bidirectional Decoding (BID), a test-time inference algorithm that bridges action chunking with closed-loop adaptation.<n>Our method boosts the performance of two state-of-the-art generative policies across seven simulation benchmarks and two real-world tasks.
  arXiv  Detail & Related papers  (2024-08-30T15:39:34Z)

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.