PhD Position F/M Scientific Claim Verification in Research Articles

1000scholars; Nantes; Presencial; EUR 24.000 - 30.000; Jornada completa

Descripción de la vacante

1000scholars in Nantes offers a PhD position focused on verifying scientific claims with multimodal evidence across text, tables, figures and citations. The PhD student will develop benchmarks and methods to align claims with supporting evidence within a multidisciplinary ANR Fabuleux project.

The role emphasizes building robust evaluation protocols and explaining verification results to authors for improving scientific writing. Collaboration across labs is expected.

Formación

• Master's degree or equivalent in Computer Science, Computational Linguistics, AI/NLP, or closely related field
• Strong background in machine learning / deep learning; NLP experience; multimodal learning is a plus
• Proficient in Python and standard deep learning frameworks (PyTorch, Hugging Face)
• Ability to design experiments, build/annotate datasets, and critically analyze model behavior
• Comfortable reading and producing scientific writing (papers, technical reports)

Responsabilidades

• Develop open benchmarks for multimodal scientific claim verification
• Create methods to identify and align claims with supporting evidence across modalities
• Design evaluation protocols assessing prediction accuracy, robustness, and evidence use
• Contribute to mechanisms for explaining verification results to authors for revision of claims

Conocimientos

Python

ML/DL

NLP

Multimodal learning

Experiment design

Scientific writing

Educación

Master's degree in Computer Science / NLP

Herramientas

PyTorch

Hugging Face Transformers

Descripción del empleo

Context

Within the framework of a partnership (you can choose between) public with French National Research Agency (ANR) Is regular travel foreseen for this post ? "travel expenses are covered within the limits of the scale in force".

Assignment

Large language models (LLMs) are increasingly used to assist scientific writing. While they can improve clarity and fluency, they may also introduce unsupported claims, distort results, or cite evidence in misleading ways. Detecting such problems requires more than analyzing the text alone: scientific claims must be checked against the evidence that supports them, which may appear in text, tables, figures, or cited papers.

Scientific claim verification has received growing attention in recent years. Early benchmarks such as SciFact introduced the task of retrieving evidence from scientific papers and determining whether it supports or refutes a claim, while later work extended this task to the more realistic and challenging multimodal setting of scientific papers, where evidence may appear in tables and figures as well as in text.

Yet, major challenges remain. Relevant evidence may be scattered across text, tables, figures, equations, code, and citations, and a correct prediction does not guarantee that a model relied on the right evidence. Developing methods that can both identify the appropriate evidence and verify claims reliably, while explaining their decisions and providing useful feedback to the user, is therefore an important step toward safer AI-assisted scientific writing.

Objective

• Find - How can we identify the evidence relevant to a scientific claim across text, tables, figures, citations, and other modalities?
• Verify - How can we determine whether a claim is supported by this evidence, while ensuring that the decision is grounded in the right evidence?
• Explain - How can verification results be explained to authors and turned into useful feedback for revising scientific claims?

Main activities

The PhD is expected to produce:

• an open benchmark for multimodal scientific claim verification;
• methods for identifying and aligning claims with supporting evidence;
• evaluation protocols that assess not only prediction accuracy, but also robustness and evidence use;
• a better understanding of the strengths and limitations of models for verifying scientific content.

Skills

Technical skills and level required :

• Master's degree (or 5-year university degree) in Computer Science, Computational Linguistics, AI/NLP, or a closely related field
• Solid grounding in machine learning / deep learning; prior exposure to NLP is expected, multimodal learning (text + tables/figures) is a plus
• Proficient in Python and standard deep learning frameworks (PyTorch, Hugging Face Transformers)
• Ability to design experiments, build/annotate datasets, and critically analyze model behavior
• Comfortable reading and producing scientific writing (papers, technical reports)

Languages :

• English: fluent, spoken and written (required for scientific publishing and daily research work)
• French: not required to apply; willingness to learn is appreciated for integration into the lab and project

Relational skills :

• Able to work autonomously while contributing to a collaborative, interdisciplinary team (this PhD is embedded in the ANR Fabuleux project)
• Clear communicator, able to explain technical results to researchers from different backgrounds
• Good listener, open to feedback, comfortable with iterative/exploratory research

Other valued appreciated :

• Experience with claim verification, fact-checking, or scientific fact/evidence retrieval
• Familiarity with retrieval-augmented generation (RAG) or multimodal document understanding
• Prior research internship, publication, or open-source contribution in NLP/ML
• Interest in AI safety / research integrity / responsible use of LLMs in science