PulseAugur
中
实时 19:59:10
English(EN) ExeBench-FHD: Addressing Fidelity Issues in Decompiler Evaluation

新的ExeBench-FHD基准改进了LLM反编译器评估

研究人员推出了ExeBench-FHD,这是ExeBench基准的一个修订版本,旨在改进基于LLM的反编译器的评估。原始的ExeBench存在九个影响反编译器测量保真度的问题,其中三个问题阻碍了C代码的恢复。ExeBench-FHD通过添加16个新字段(包括调用点汇编和数据段)以及五个警告标志来解决这些问题。评估表明,ExeBench-FHD可以显著提高GPT-6 Sol等模型在特定类型函数上的重新执行率。 AI

影响 这一改进的基准将允许对基于LLM的反编译器进行更准确的评估,从而可能带来更好的代码生成和分析工具。

排序理由 该集群描述了在arXiv上发表的一篇新的基准论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新的ExeBench-FHD基准改进了LLM反编译器评估

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了在arXiv上发表的一篇新的基准论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
7 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Akarsh Ashok, Dinil Mon Divakaran, Vivek Balachandran ·

    ExeBench-FHD:解决反编译器评估中的保真度问题

    arXiv:2610.28212v1 Announce Type: cross Abstract: ExeBench is one of the most widely used benchmarks for evaluating LLM-based decompilers. We analyze ExeBench and identify nine issues that affect how faithfully a test measures a decompiler. Three of them prevent LLM decompilers f…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    ExeBench-FHD: Addressing Fidelity Issues in Decompiler Evaluation

    ExeBench is one of the most widely used benchmarks for evaluating LLM-based decompilers. We analyze ExeBench and identify nine issues that affect how faithfully a test measures a decompiler. Three of them prevent LLM decompilers from recovering C code from ExeBench's function. Th…