6 accepted papers
Pretrained language models can acquire novel tasks either through in-context learning (ICL)---adapting behavior via activations without weight updates---or through supervised fine-tuning (SFT), where parameters are explicitly updated. Prior work has reported differences in their generalization perfo…
Current training data attribution (TDA) methods treat influence as static, ignoring the fact that neural networks learn in distinct stages. This stagewise development, driven by phase transitions on a degenerate loss landscape, means a sample's importance is not fixed but changes throughout training…
By virtue of linguistic compositionality, few syntactic rules and a finite lexicon can generate an unbounded number of sentences. That is, language, though seemingly high-dimensional, can be explained using relatively few degrees of freedom. An open question is whether contemporary language models (…
Why do biological and artificial neurons sometimes modularise, each encoding a single meaningful variable, and sometimes entangle their representation of many variables? In this work, we develop a theory of when biologically inspired networks---those that are nonnegative and energy efficient---modul…
We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72–95\% of their original top-1 prediction accuracy without any fine-tuning. We find that performance degradation is not un…
Diverse studies in systems neuroscience begin with extended periods of curriculum training known as ‘shaping’ procedures. These involve progressively studying component parts of more complex tasks, and can make the difference between learning a task quickly, slowly or not at all. Despite the importa…