3 papers
cs.CL2026
Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models
Alexandrine Fortier, Hazel Chen, Peter West
The lack of diversity in LM content is widely attributed to the alignment process, but how and where exactly in the pipeline this collapse begins is unknown. We argue that output h…
cs.CL2026
Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
Alexandrine Fortier, Thomas Thebaud, Jesús Villalba +3
Speech language models (SLMs) are systems of systems: independent components that unite to achieve a common goal. Despite their heterogeneous nature, SLMs are often studied end-to-…
cs.SD2025
Multi-Target Backdoor Attacks Against Speaker Recognition
Alexandrine Fortier, Sonal Joshi, Thomas Thebaud +3
In this work, we propose a multi-target backdoor attack against speaker identification using position-independent clicking sounds as triggers. Unlike previous single-target approac…