activity
20242026
collaborators

5 papers

cs.CL2026

Multi-Hop Knowledge Composition is Bound by Pretraining Exposure

Yannis Karmim, Luis Marti, Djamé Seddah +1

Large Language Models fail at implicit multi-hop reasoning: a model answers "When was born?" and "Who is 's closest friend?" correctly but fails on "When was 's closest f…

cs.SE2026

Building Specialized Software-Assistant ChatBot with Graph-Based Retrieval-Augmented Generation

Mohammed Hilel, Yannis Karmim, Jean De Bodinat +2

Digital Adoption Platforms (DAPs) have become essential tools for helping employees navigate complex enterprise software such as CRM, ERP, or HRMS systems. Companies like LemonLear…

cs.CL2026

Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America

Yannis Karmim, Renato Pino, Hernan Contreras +6

Large Language Models (LLMs) exhibit inequalities with respect to various cultural contexts. Most prominent open-weights models are trained on Global North data and show prejudicia…

cs.CV2025

ViLU: Learning Vision-Language Uncertainties for Failure Prediction

Marc Lafon, Yannis Karmim, Julio Silva-Rodríguez +6

Reliable Uncertainty Quantification (UQ) and failure prediction remain open challenges for Vision-Language Models (VLMs). We introduce ViLU, a new Vision-Language Uncertainty quant…

cs.LG2024

Supra-Laplacian Encoding for Transformer on Dynamic Graphs

Yannis Karmim, Marc Lafon, Raphael Fournier S'niehotta +1

Fully connected Graph Transformers (GT) have rapidly become prominent in the static graph community as an alternative to Message-Passing models, which suffer from a lack of express…