2025
Context Copying Modulation: The Role of Entropy Neurons in Managing Parametric and Contextual Knowledge Conflicts
Zineddine Tighidet, Andrea Mogini, Hedi Ben younes, Jiali Mei, Patrick Gallinari, Benjamin Piwowarski
EMNLP 2025
The behavior of Large Language Models (LLMs) when facing contextual information that conflicts with their internal parametric knowledge is inconsistent, with no generally accepted explanation for the expected outcome distribution. Recent work has identified in autoregressive transformer models a cla