Dumas, Clément
- Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
2025/04/03 by Julian Minder, Clément Dumas, Minder, Julian +7 · 3 voices · 5 citations
#cs.LG #cs.AI #cs.CL
- Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
2024/11/13 by Dumas, Clément, Chris Wendler, Veniamin Veselovsky +6 · 5 citations
Computer Science · Neuroscience · #Natural Language Processing Techniques #Neurobiology of Language and Bilingualism #Speech and dialogue systems
- Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
2025/12/17 by Adam Karvonen, James Chua, Karvonen, Adam +19 · 1 voice · 1 citation
Computer Science · Medicine · #Artificial Intelligence in Healthcare and Education #Explainable Artificial Intelligence (XAI) #Topic Modeling #cs.AI #cs.CL #cs.LG