Papers by Matthieu Tehenan
Semantic Geometry of Sentence Embeddings (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Sentence embeddings are central to natural language processing, but their internal features are not interpretable and users lack fine-grained control for downstream tasks. |
| Approach: | They propose a formal framework to characterize the organization of features in sentence embeddings . they show how they can be composed to capture richer semantic structures . |
| Outcome: | The proposed method can be used to capture richer semantic structures. |
MPTA: MultiTask Personalization Assessment (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MTPA tests large language models on real personas spanning demographics, beliefs, and values . aggregate metrics suggest models are truthful and safe, subgroup-specific evaluations reveal hidden pockets of degraded factuality, fairness disparities, and inconsistent value alignment. |
| Approach: | a benchmark is a tool that leverages large-scale survey data to construct real personas . they show persona conditioning exposes pluralistic misalignment . |
| Outcome: | MTPA conditions models on real personas and tests their behavior across alignment tasks. |