4 papers
Compact Path Representation in DAGs via Colored Edge Pebbling
Paola Bonizzoni, Alessio Conte, Gianluca Della Vedova +3
Compactly representing a variation graph is a core problem in computational pangenomics that is usually attacked with techniques that have been originated on texts and adapted to g…
Tracing Persona Vectors Through LLM Pretraining
Viktor Moskvoretskii, Dominik Glandorf, Jorge Medina Moreira +2
How large language models internally represent high-level behaviors is a core interpretability question with direct relevance to AI safety: it determines what we can detect, audit,…
Controllable Context Sensitivity and the Knob Behind It
Julian Minder, Kevin Du, Niklas Stoehr +4
When making predictions, a language model must trade off how much it relies on its context vs. its prior knowledge. Choosing how sensitive the model is to its context is a fundamen…
Activation Scaling for Steering and Interpreting Language Models
Niklas Stoehr, Kevin Du, Vésteinn Snæbjarnarson +3
Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant act…