← Back to all news
arXiv AI By Lucius Bushnaq, Dan Braun, Oliver Clive-Griffin, Bart Bussmann, Nathan Hu, Michael Ivanitskiy, Linda Linsefors, Lee Sharkey

Interpreting Language Model Parameters

Read the original on arXiv AI →

The paper introduces adVersarial Parameter Decomposition (VPD), a method that splits a language model’s parameters into simple subcomponents, each responsible for a small part of the model’s algorithm. VPD optimizes these decompositions so that the model’s input‑output behavior remains intact even when many subcomponents are removed, including adversarially chosen ones. This approach enables a new form of circuit analysis by tracing how sequences of parameter subcomponents interact to produce outputs for specific inputs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 11

Perturbation: A simple and efficient adversarial tracer for representation learning in language models

The paper introduces Perturbation, a method that treats representations in language models as learning conduits rather than activation patterns. By fine‑tuning a model on a single adversarial example and observing how this perturbation spreads to other inputs, the approach avoids geometric assumptions and does not identify representations in untrained models. In trained models, Perturbation uncovers structured transfer across multiple linguistic scales, indicating that language models generalize along representational lines and acquire linguistic abstractions through experience.

By Joshua Rozner, Cory Shain
llmsfine-tuningsafety
More like this →