EQDAT-RE: An Explainable Qualitative Data Analysis for Transparent Requirements Engineering
Bibliographic record
Abstract
Requirements Engineering (RE) in regulated domains demands not only accurate extraction of domain entities from natural language requirements but also transparent, verifiable, and auditable decision-making processes. While Large Language Models (LLMs) show promise for automating entity extraction using Qualitative Data Analysis (QDA) techniques, their black-box nature limits adoption by failing to provide explainable outputs. To bridge this gap, we introduce EQDAT-RE (Explainable QDA for Transparent RE), a novel framework that embeds explainability directly into each phase of the extraction process. EQDAT-RE implements a multi-stage pipeline combining LLM-based entity extraction with decision trace generation, multi-perspective cross-validation, symbolic linguistic verification, contrastive counterfactual testing, and feedback-driven refinement. Our evaluations across four domain-specific datasets demonstrate that EQDAT-RE achieves an average extraction accuracy of 87% while generating explanations with over 92% completeness, 91% consistency, and 89% faithfulness. By systematically embedding structured explainability mechanisms, EQDAT-RE enhances trust, supports regulatory compliance, and enables scalable, audit-ready automation of requirements analysis in safety-critical and regulated software domains.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.007 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.006 |
| Open science | 0.007 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".