Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning

NeurIPSSpotlight2025

Authors
Navita Goyal, Hal Daumé III, Alexandre Drouin, Dhanya Sridhar
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Language model activations entangle concepts that mediate their behavior, making it difficult to interpret these factors, which has implications for generalizability and robustness…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

representation learning language model robustness causal

← All NeurIPS 2025 Spotlight papers · Browse the whole archive