We have 6 of 88 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Transformer language models (LMs) are feed-forward: deep-layer representations are never fed back to shallower layers, and the only pathway for information to flow downward across generation steps is the decoded token. This narrow channel forces models to recompute intermediate results and to discard alternative contin...
This work leverage Mixture of Factor Analyzers (MFA) as a scalable, unsupervised alternative that models the activation space as a collection of Gaussian regions with their local covariance structure, and positions local geometry, expressed through subspaces, as a promising unit of analysis for scalable concept discove...
This work establishes that precise embedding-level intervention is necessary for robust concept erasure, and demonstrates that existing methods can benefit from such augmentation, with minimal coherence loss.
This work introduces a controlled setting to study the causes and training dynamics of cross-lingual knowledge transfer by training small Transformer models from scratch on synthetic multilingual datasets and suggests methods to encourage representational unification as part of training that would improve LLMs'cross-li...
LMEnt is released to support studies of knowledge in LMs, including knowledge representations, plasticity, editing, attribution, hallucinations, and learning dynamics, finding that entity co-occurrence and mention forms—which are difficult to study with existing tools—affect learning trends.
The findings suggest that what the model knows and how it is asked are intertwined in parameter space, undermining the "knowledge base"alogy and carrying implications for the reliability and controllability of factual knowledge in LMs.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
