From the 1 of 3 linked papers with an AI index.
3 papers
Can Graph Learning Learn Circuits?
Chester Tan, Moritz Lampert, Courtney Maynard +3
Circuit localization is a mechanistic interpretability task whose goal is to identify a sparse subgraph of a transformer's computation graph sufficient to reproduce a particular be…
Belief Coevolution in a Social Network of Generalist and Specialist Large Language Models
Germans Savcisens, Samantha Dies, Courtney Maynard +1
The paper presents CoevolveSim, a simulation framework for studying how beliefs spread and evolve among interacting generalist and specialist large language models in a social netw…
Epistemic Familiarity is Associated With Belief Stability in Large Language Models
Samantha Dies, Courtney Maynard, Germans Savcisens +1
Large language models (LLMs) are widely used as information sources, yet small changes in semantic assumptions can destabilize their beliefs. We introduce P-StaT (Perturbation Stab…