Graph neural networks on assurance case graphs reach 0.76 ROC-AUC for link prediction and 0.94 F1 for distinguishing human from LLM-generated cases, with observed differences in hierarchical linking patterns.
Classification or prompting: A case study on legal requirements traceability
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
TraceLLM uses prompt engineering and label-aware demonstration selection with eight LLMs on four benchmark datasets to achieve state-of-the-art F2 scores for requirements traceability, outperforming IR baselines and prior LLM methods.
ProReFiCIA uses LLMs with tailored prompts to identify impacted requirements, achieving 85.7% recall on unseen industrial data while requiring review of only 3% of requirements, rising to 95.7% recall with RAG at 3.6% review cost.
Targeted data selection from source domains reduces negative transfer when adapting compliance detection models to new regulations.
citing papers explorer
-
Evaluating Assurance Cases as Text-Attributed Graphs for Structure and Provenance Analysis
Graph neural networks on assurance case graphs reach 0.76 ROC-AUC for link prediction and 0.94 F1 for distinguishing human from LLM-generated cases, with observed differences in hierarchical linking patterns.
-
TraceLLM: Leveraging Large Language Models with Prompt Engineering for Enhanced Requirements Traceability
TraceLLM uses prompt engineering and label-aware demonstration selection with eight LLMs on four benchmark datasets to achieve state-of-the-art F2 scores for requirements traceability, outperforming IR baselines and prior LLM methods.
-
LLM-Driven Cost-Effective Requirements Change Impact Analysis
ProReFiCIA uses LLMs with tailored prompts to identify impacted requirements, achieving 85.7% recall on unseen industrial data while requiring review of only 3% of requirements, rising to 95.7% recall with RAG at 3.6% review cost.
-
Cross-Domain Data Selection and Augmentation for Automatic Compliance Detection
Targeted data selection from source domains reduces negative transfer when adapting compliance detection models to new regulations.