ExArch: Enabling Architecture Traceability by LLM-based Architecture Component Name Extraction

Dominik Fuchß; Haoyu Liu; Tobias Hey; Jan Keim; Anne Koziolek

doi:10.18420/se2026_20

January 1, 2026Open Access

ExArch: Enabling Architecture Traceability by LLM-based Architecture Component Name Extraction

View Full Paper

Ask AI

Bookmark

Share

Key Points

The aim is to enhance traceability between software architecture documentation and source code through LLMs.
Exploration of traceability link recovery (TLR)
Utilization of large language models (LLMs)
Analysis of software architecture documentation and source code
Improved traceability link recovery between SAD and source code
Efficient generation of intermediate artifacts through LLMs

Implication

This investigation demonstrates the recovery of traceability links between software architecture documentation and source code using LLMs, implying improved documentation practices.

Abstract

Our paper [Fu25], published at the 22nd IEEE International Conference on Software Architecture (ICSA), investigates traceability link recovery ( TLR ) between software architecture documentation (SAD) and source code, leveraging large language models (LLMs) to generate intermediate artifacts.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Fuchß et al. (2026) studied this question.

synapsesocial.com/papers/698828d90fc35cd7a8848a8b https://doi.org/10.18420/se2026_20

View Full Paper

Ask AI

Bookmark

Share

ExArch: Enabling Architecture Traceability by LLM-based Architecture Component Name Extraction

Key Points

Implication

Abstract

Discussion

Cite This Study

ExArch: Enabling Architecture Traceability by LLM-based Architecture Component Name Extraction

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading