4 papers
Discovering Latent Groups for Robust Classification
Ankur Garg, Ulrich Aïvodji, Samira Ebrahimi Kahou +1
Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented subgroups. Existing methods address this b…
Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
Xuemin Yu, Ankur Garg, Samira Ebrahimi Kahou +1
Large language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information these internal representations capture…
Cross-Layer Discrete Concept Discovery for Interpreting Language Models
Ankur Garg, Xuemin Yu, Hassan Sajjad +1
Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer…
Discrete Causal Representations from Heterogeneous Domains: A Bayesian Approach with Social Survey Applications
Ankur Garg, Michael Stettler, Aaron Schein +1
Causal representation learning aims to infer the high-level latent causal concepts that give rise to observed low-level measurements. This is particularly relevant for heterogeneou…