Work

Guarding LLM-aided Software Transformation Tasks via Component Exoskeletons

Year: 2025

Type: conference-paper

Abstract: Large language models (LLMs) are achieving state-of-the-art results across a wide variety of software transformation tasks---including translating across languages and lifting opaque software components to high-level languages. Unfortunately, their results are often subtly incorrect, insecure, or underperformant---affecting the widespread deployment of these LLM-driven techniques in settings that go beyond the narrow scope of academic papers. This paper posits that such widespread deployment crucially depends on developing appropriate model guardrails for safeguarding the results of the transformation process. Such guardrails can be supported by component exoskeletons, tunable partial specifications extracted mostly automatically from the original, pre-transformed component. Exoskeletons serve as component projections that supplement, and often go through, the entire transformation process, confirming that the new, transformed component meets the original specifications. They show promise on several real-world scenarios and unearth exciting research directions.

Source: Workshop on Practical Adoption Challenges of ML for Systems (PACMI)

DOI: 10.1145/3766882.3767171

Authors: Evangelos Lamprou, Christian Gram Kalhauge, Martin C. Rinard, Nikos Vasilakis

Institutions: Brown University, Technical University of Denmark, Massachusetts Institute of Technology

Language: English

Topic: Software Engineering Research

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, Defense Advanced Research Projects Agency

Awards: G2796279259, Collaborative Research: SaTC: CORE: Medium: Securing Continuous Integration Workflows