6 papers
Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution
Matthew Kowal, Goncalo Paulo, Louis Jaburi +6
As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones.…
Interpreting Physics in Video World Models
Sonia Joseph, Quentin Garrido, Randall Balestriero +5
A long-standing question in physical reasoning is whether video-based models need to rely on factorized representations of physical variables in order to make physically accurate p…
Emergent Persuasion: Will LLMs Persuade Without Being Prompted?
Vincent Chang, Thee Ho, Sunishchal Dev +4
With the wide-scale adoption of conversational AI systems, AI are now able to exert unprecedented influence on human opinion and beliefs. Recent work has shown that many Large Lang…
It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics
Matthew Kowal, Jasper Timm, Jean-Francois Godbout +6
Persuasion is a powerful capability of large language models (LLMs) that both enables beneficial applications (e.g. helping people quit smoking) and raises significant risks (e.g.…
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
Thomas Fel, Ekdeep Singh Lubana, Jacob S. Prince +7
Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dicti…
Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
Harrish Thasarathan, Julian Forsyth, Thomas Fel +2
We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing…