arXiv cs.CL· Tanu Singh, Aashna Suman, Vinod Patidar·· 13 小时前AI 评分31
HiddenLens：检测与消解软件需求隐藏假设的多层 LLM 框架
HiddenLens: A Multi-Layer LLM Framework for Detecting and Resolving Hidden Assumptions in Software Requirements
AI 导读
HiddenLens 是一个六层 BERT-LLM 流水线，用于检测、分类、质询并消解软件需求中的隐藏假设，端到端 F1 达 0.79，较关键词基线和 QuARS-Adapted 基线分别高出 71% 和 61%。其 BERT 非功能需求分类器 F1 为 0.847，并配套发布含 312 条需求、847 个隐藏假设标注的 HiddenLens Corpus（HLC）数据集。
正文 · 原文
Abstract:Natural-language software requirements often omit assumptions about performance, operating conditions, user behaviour, and domain constraints, affecting architecture, testing, and deployment. If undiscovered until implementation, resolving them is far more costly than addressing them early. Although ambiguity and vagueness are widely studied, less attention has been given to assumptions embedded in requirements that appear clear and reasonable. We propose HiddenLens, a novel six-layer BERT-LLM pipeline and, to our knowledge, the first framework engineered to detect, classify, question, and resolve hidden assumptions rather than merely flag ambiguity. Layer 1 uses BERT attention entropy to localise unresolved spans; Layer 2 uses CoT-prompted LLM reasoning to articulate each assumption and its failure risk; Layer 3 uses fine-tuned BERT to classify assumptions into six non-functional requirement categories: performance, security, scalability, usability, reliability, and domain; Layer 4 generates ranked clarification options using FS LLM prompting; Layer 5 enables human validation through confirmation, editing, or rephrasing; and Layer 6 rewrites the requirement using the confirmed resolution, producing an explicit, testable, and traceable requirement. We also introduce the HiddenLens Corpus (HLC), comprising 312 requirements annotated with 847 hidden assumptions across six NFR categories. Inspired by PROMISE and PURE, HLC addresses the lack of annotated data for this task and is, to our knowledge, the first dataset developed specifically for it. HiddenLens outperforms keyword-based and QuARS-Adapted baselines by 71% and 61%, respectively, achieving an end-to-end F1-score of 0.79; its BERT-based NFR classifier achieves an F1-score of 0.847. These results indicate that HiddenLens can help analysts resolve hidden assumptions before they propagate through software development.
| Comments: | 24 pages, 14 figures, 10 tables |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.29996 [cs.SE] |
| (or arXiv:2610.29996v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29996 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Vinod Patidar [view email]
[v1]
Wed, 21 Oct 2026 16:35:35 UTC (2,307 KB)
来源：arXiv cs.CL · arxiv.org