PulseAugur
实时 08:30:02
English(EN) Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory Study

大型语言模型在从代码提交中提取设计决策方面显示出潜力,但缺乏理由

一项初步研究探讨了大型语言模型(LLM)从源代码提交中提取架构设计决策的有效性。研究人员使用零样本和少样本提示,在 30 个开发人员编写的决策上测试了四种大型语言模型——Gemini 3-ProDeepSeek-R1Kimi K2Qwen3。虽然所有模型都达到了高于 0.81 的 BERT-F1 分数,但少样本提示显示出轻微的改进。然而,生成的决策通常过长、侧重于实现,并且缺乏根本原因,这表明需要更具架构意识的大型语言模型系统。 AI

影响 强调了软件工程和自动化知识管理中具有架构意识的大型语言模型系统的机遇。

排序理由 该集群包含一篇详细介绍大型语言模型能力研究的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

大型语言模型在从代码提交中提取设计决策方面显示出潜力,但缺乏理由

本文如何被排名

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍大型语言模型能力研究的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
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
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Amey Karan, Rudra Dhar, Mohamed Soliman, Karthik Vaidhyanathan ·

    大型语言模型能否从源代码提交中提取建筑设计决策?——一项初步探索性研究

    arXiv:2609.03721v1 Announce Type: cross Abstract: Context: Architectural Design Decisions (ADDs) capture the rationale behind the structure and evolution of software systems but are rarely documented explicitly, and are often hidden inside source code commits. Recovering them is …