Megha Sudheendran

Biography:

Supervisors: Larisa Safina & Nicolas Anquetil · Team: Rmod, Inria Lille · Lab: CRIStAL, UMR 9189 CNRS

A Study of Prompting Strategy for Low-Resource Legacy Language Migration

Megha Sudheendran, Larisa Safina, Nicolas Anquetil

Submitted 2025 · Under review — ICPC 2027, International Conference on Program Comprehension

Large language models (LLMs) have been applied to code migration between programming languages. Code migration is more difficult than code generation because it requires comprehending the source program, including all language-specific constructs of the source language. We investigate this problem by migrating FORTRAN 77 with a proprietary extension to Fortran 2008. Because the proprietary extension has close to zero public resources, the migration must rely on knowledge supplied via in-context prompting. We study five prompt configurations with a "prompt ablation" approach to systematically evaluate the individual contribution of migration rules, legacy structured type definitions, project source context, and one-shot example. We assess their impact on textual similarity (ChRF), runtime behaviour, and adherence to informal business requirements.

Legacy System Migration LLMs for Code Code Translation Prompt Ablation Fortran
2026 – 2027

Introduction to Software Development — Labs

Teaching Assistant · IUT Lille

2025 – 2026

Introduction to Software Development — Labs

Teaching Assistant · IUT Lille

2025 –

PhD Student — LLM for Fortran Migration

Inria Lille / CRIStAL, Université de Lille

Lille, France

2024 – 2025

AI / ML Engineer

Mind7 Consulting

Paris, France — RAG-based systems on Azure OpenAI, prompt engineering

2023 – 2024

Data Engineer

apiday

Paris, France — BERT sentence transformers, cloud functions, data pipelines

2022 – 2023

Data Scientist (Intern)

TIBCO Inc.

Paris, France — AIaaS components, CI/CD for ML, Spotfire

2021 – 2023

MSc Artificial Intelligence Systems

EPITA — École pour l'informatique et les techniques avancées

Paris, France

2016 – 2019

Android Developer

Srishti Innovative Computer Systems

Trivandrum, India

2009 – 2013

BTech Computer Science & Engineering

University of Kerala

Trivandrum, India

Nov 2026

DéfiThon AI4SE 2026

GDR SciLog · Berger-Levrault, Toulouse INP, IRIT

16–17 November 2026 · Labège (Toulouse), France

First edition of this collaborative hackathon-style event designed by and for young researchers, focusing on AI for Software Engineering (AI4SE). Organised as part of the GDR SciLog national research network.

Jun 2026

1er Congrès des Sciences du Logiciel — SciLog 2026

GDR SciLog · CNRS, Université de Lille, Polytech Lille

1–4 June 2026 · Polytech Lille, Cité Scientifique, Villeneuve-d’Ascq, France

National congress of software science researchers (GDR SciLog), held alongside the AFADL conference on formal approaches to software development. Brought together doctoral students, researchers, and industry professionals to share ideas, demos, posters, and recent results.

Nov 2025

LLM4Code Annual Meeting 2025

Inria · Team member, Inria Lille

14 November 2025 · Centre Inria Paris, 48 Rue Barrault, 75013 Paris

Annual gathering of the LLM4Code Inria project — Reliable and Productive Code Assistants based on Large Language Models. The day covered a broad range of topics including software migration and modernisation, code completion for large projects, LLM-based software engineering agents, self-improving models for program synthesis, and use cases for training, fine-tuning and benchmarking.