PhD in Multimodal AI for Scientific Claim Verification

1000scholars; Nantes; Sur place; EUR 24 000 - 30 000; Plein temps

Résumé du poste

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.

Qualifications

• 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)

Responsabilités

• 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

Connaissances

Python

ML/DL

NLP

Multimodal learning

Experiment design

Scientific writing

Formation

Master's degree in Computer Science / NLP

Outils

PyTorch

Hugging Face Transformers

Description du poste

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.