SupportVectors: Generative AI, LLMs, Machine Learning

This week, we will walk through and discuss of the paper: R2Code: A Self-Reflective LLM Framework for Requirements-to-Code Traceability [https://arxiv.org/pdf/2604.22432]

Abstract of the Paper:
Accurate requirement-to-code traceability is crucial for software maintenance. However, existing IR- and embedding-based methods are heavily dependent on lexical similarity, often yielding incomplete or inconsistent links across projects and languages and incurring high cost from long-context retrieval and prompting. This paper presents R2Code, an LLM-based semantic traceability framework designed to improve trace link accuracy while reducing inference cost. R2Code integrates three components: 1) a decomposition-enhanced Bidirectional Alignment Network (BAN) that aligns four-layer requirement semantics with corresponding code structures to support cross-level semantic matching; 2) a Self-Reflective Consistency Verification (SRCV) module that conducts explanation-guided consistency checking to calibrate link reliability; and 3) a Dynamic Context-Adaptive Retrieval (DCAR) mechanism that adjusts retrieval granularity and filters contexts using semantic-overlap weighting for efficient context utilization. Experiments on five public datasets spanning multiple domains and two programming languages demonstrate that R2Code consistently outperforms the strongest baselines, achieving an average F1 gain of 7.4%, while reducing token consumption by up to 41.7% through adaptive context control.

-----------------

We are a group of applied AI practitioners and enthusiasts who have formed a collective learning community. We hold our research paper reading seminar covering an AI topic weekly. One member carefully explains the paper, making it more accessible to a broader audience. Then, we follow this reading with a more informal discussion and socializing.
You are welcome to join this in person or over Zoom.