Newest papers

HiddenLens: A Multi-Layer LLM Framework for Detecting and Resolving Hidden Assumptions in Software Requirements

Tanu Singh, aashna suman, Vinod Patidar · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29996 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Эти требования к программному обеспечению, основанному на естественном языке, часто оставляют без внимания предположения о производительности, эксплуатационных условиях, поведении пользователей и ограничениях домена, которые влияют на архитектуру, тестирование и развертывание. Если они не были обнаружены до реализации базового уровня, их решение значительно дороже, чем их раннее решение. Хотя неоднозначность и неоднозначность широко изучаются, меньше внимания уделяется предположениям, встроенным в требования, которые кажутся ясными и разумными. Мы предлагаем HiddenLens, новый шестислойный трубопровод BERT-LLM и, по нашему мнению, первая рамка, разработанная для обнаружения, классификации, классификации и решения скрытых предположений, а не просто обозначения двусмысленности. Уровень 1 использу

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Vagueness, Ambiguity, Software, Layer (electronics), Classifier (UML)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange