Showing 2026Show all
3 papers · 1 filter
cs.CL2026
Some Emotions Run Deeper: Layer-wise Probing and Causal Intervention in Large Language Models
Tian Fang, Gaël Guibon, Davide Buscaldi
Emotion is expressed in text along a wide spectrum, from surface lexical cues to inferences entangled with content. Most layer-wise analyses of emotion in LLMs use a single corpus,…
cs.LG2026
Benchmarking Generalization in Financial Statement Fraud Detection: robust evaluation and novel tasks
Guy Stephane Waffo Dzuyo, Gaël Guibon, Christophe Cerisara +1
Financial statement fraud detection (FSFD) is crucial for market integrity but faces challenges from increasingly sophisticated schemes and under-utilized textual data in financial…
cs.CL2026
Conversational Control with Ontologies for Large Language Models: A Lightweight Framework for Constrained Generation
Barbara Gendron, Gaël Guibon, Mathieu d'Aquin
Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies cha…