Researchers have developed HiddenLens, a novel six-layer framework that utilizes BERT and LLMs to identify and resolve hidden assumptions within software requirements. This framework aims to address the costly issue of undiscovered assumptions that can impact software architecture and testing. HiddenLens categorizes assumptions into six non-functional requirement types and generates clarification options, ultimately rewriting requirements to be explicit and testable. The system was evaluated using the newly introduced HiddenLens Corpus (HLC), outperforming baseline methods and achieving a high F1-score. AI
IMPACT This framework could improve software development by ensuring requirements are more explicit and testable, reducing downstream costs.
RANK_REASON The cluster describes a novel framework and dataset presented in a research paper. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
