PhD Candidate (M/F) - Natural Language Processing - Using Large Language Models for scientific writing
New
- FTC PhD student / Offer for thesis
- 36 months
- Doctorate
This offer is available in English version
This offer is open to people with a document recognizing their status as a disabled worker.
Offer at a glance
The Unit
Laboratoire lorrain de recherche en informatique et ses applications
Contract Type
FTC PhD student / Offer for thesis
Working hHours
Full Time
Workplace
54506 VANDOEUVRE LES NANCY
Contract Duration
36 months
Date of Hire
01/12/2026
Remuneration
2300 € gross monthly
Apply Application Deadline : 11 November 2026 23:59
Job Description
Thesis Subject
The landscape of scientific publishing is currently undergoing rapid change. The volume of published research continues to grow at an unprecedented rate, placing increasing pressure on journals, conferences and the peer-review process. Peer review, the cornerstone of scientific validation, is under severe strain and risks becoming unsustainable. Preserving the reliability and integrity of scientific publications has therefore become a crucial issue.
Large language models (LLMs) play a central role in this transformation. Their rapid adoption meets genuine needs in terms of writing assistance and, more broadly, research support. They can help to revise drafts, improve readability and express complex ideas more clearly. However, their use in scientific writing gives rise to new and significant risks: from fabricated or distorted content to manipulated citations, including subtle forms of plagiarism, and even the large-scale production of unreliable or fraudulent articles.
This doctoral thesis aims to improve the usefulness of large language models (LLMs) in the context of scientific writing. We aim to identify inconsistencies, distortions and unjustified changes introduced during the revision process – whether these stem from the model, the authors or their interaction – and to design feedback mechanisms incorporating LLMs that help researchers to iteratively improve their writing and strengthen their writing practices, whilst allowing them to retain control over the writing process.
Your Work Environment
Loria is the French acronym for the “Lorraine Research Laboratory in Computer Science and its Applications” and is a research unit (UMR 7503), common to CNRS, the University of Lorraine, CentraleSupélec and Inria. This unit was officially created in 1997.
The successful candidate will be offered a PhD contract and will be enrolled at the University of Lorraine's Doctoral School of Computer Science, Automation, Electronics and Mathematics (IAEM).
Loria's missions mainly deal with fundamental and applied research in computer sciences.
Bolstered by the 500 people working in the lab, its scientific work is conducted in 24 teams including 13 common teams with Inria. Loria is today one of the biggest research labs in the Grand Est Region.
Constraints and risks
Annual progress meetings will be held at the project's partner laboratories in Nantes and Paris.
Compensation and benefits
Compensation
2300 € gross monthly
Annual leave and RTT
44 jours
Remote Working practice and compensation
Pratique et indemnisation du TT
Transport
Prise en charge à 75% du coût et forfait mobilité durable jusqu’à 300€
About the offer
| Offer reference | UMR7503-YANPAR-003 |
|---|---|
| CN Section(s) / Research Area | Information sciences: processing, integrated hardware-software systems, robots, commands, images, content, interactions, signals and languages |
About the CNRS
The CNRS is a major player in fundamental research on a global scale. The CNRS is the only French organization active in all scientific fields. Its unique position as a multi-specialist allows it to bring together different disciplines to address the most important challenges of the contemporary world, in connection with the actors of change.
Create your alert
Don't miss any opportunity to find the job that's right for you. Register for free and receive new vacancies directly in your mailbox.