3 papers
cs.LG2026
Interpretability Can Be Actionable
Hadas Orgad, Fazl Barez, Tal Haklay +9
Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impa…
cs.CL2026
The Illusion of Superposition? A Principled Analysis of Latent Thinking in Language Models
Michael Rizvi-Martel, Guillaume Rabusseau, Marius Mosbach
Latent reasoning via continuous chain-of-thoughts (Latent CoT) has emerged as a promising alternative to discrete CoT reasoning. Operating in continuous space increases expressivit…
cs.CL2025
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Daniela Gottesman, Alon Gilae-Dotan, Ido Cohen +4
Language models (LMs) increasingly drive real-world applications that require world knowledge. However, the internal processes through which models turn data into representations o…