R2Code improves requirement-to-code traceability with a bidirectional alignment network, self-reflective consistency verification, and dynamic context-adaptive retrieval, yielding 7.4% average F1 gain and up to 41.7% lower token use on five datasets.
Llm- based class diagram derivation from user stories with chain-of-thought promptings,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Multi-level alignment hints based on conversational dynamics improve scam detection accuracy and support earlier confidence formation compared with keyword alerts.
citing papers explorer
-
R2Code: A Self-Reflective LLM Framework for Requirements-to-Code Traceability
R2Code improves requirement-to-code traceability with a bidirectional alignment network, self-reflective consistency verification, and dynamic context-adaptive retrieval, yielding 7.4% average F1 gain and up to 41.7% lower token use on five datasets.
-
Making Sense of Scams: Understanding Scam Conversations Through Multi-Level Alignment
Multi-level alignment hints based on conversational dynamics improve scam detection accuracy and support earlier confidence formation compared with keyword alerts.