English(EN) Confidence-Gated Transductive Test Generation for Code Reranking

新方法改进了LLM生成代码的测试用例生成

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-14 04:00

研究人员开发了一种名为置信门控归纳测试生成（CoTT）的新方法，以改进大型语言模型（LLMs）生成程序的测试用例合成。CoTT使用一种高效的归纳程序，并且仅在归纳置信度低时才诉诸计算密集度更高的归纳生成。这种自适应方法在优化计算资源的同时提高了测试用例输出的可靠性。在代码重排序基准上的实验表明，CoTT在性能和效率上均优于现有基线，证明了使用单个LLM进行基于置信度的计算分配的好处。 AI

影响该方法可以增强大型语言模型生成代码的评估和可靠性。

排序理由该集群包含一篇详细介绍测试用例生成新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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

本文如何被排名

Signal score: 26 / 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测试用例生成新方法的论文。[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]

arXiv cs.CL TIER_1 English(EN) · Sungjae Lee, Youngsik Yoon, Seockbean Song, Siwei Wang, Wei Chen, Jungseul Ok · 2026-09-14 04:00

用于代码重排序的置信度门控传导性测试生成

arXiv:2609.12489v1 Announce Type: cross Abstract: Test case synthesis is crucial for evaluating and ranking programs generated by large language models (LLMs). However, constructing high-quality test cases remains challenging because reliable expected outputs are often difficult …

本文如何被排名

报道来源 [1]

用于代码重排序的置信度门控传导性测试生成

相关实体

相关话题