12 citations · 12 across the 18 of their papers we have counts for
4 papers · 1 filter
Don't Forget! Decomposing the Training Dynamics of Memorization in Language Models
Florian Eichin, Philipp Mondorf, Andrei Mircea +3
Memorization has been proposed as a mechanism to explain how language models fit the tail of their training distributions, but its training dynamics are not understood well. In thi…
Tracing Uncertainty in Language Model "Reasoning"
Nils Grünefeld, Bertram Højer, Philipp Mondorf +5
Language model (LM) "reasoning", commonly described as Chain-of-Thought or test-time scaling, often improves benchmark performance, but the dynamics underlying this process remain…
ExPLAIND: Unifying Model, Data, and Training Attribution to Study Model Behavior
Florian Eichin, Yupei Du, Philipp Mondorf +3
Post-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation, and are often tied to a particular level of g…
Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
Philipp Mondorf, Sondre Wold, Barbara Plank
A fundamental question in interpretability research is to what extent neural networks, particularly language models, implement reusable functions through subnetworks that can be co…