6 papers
Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
Nan Chen, Zhouhao Yang, Soufiane Hayou
Intent classification in Large Language Models (LLMs) involves categorizing user prompts into predefined classes. For instance, given a user prompt, the system must determine wheth…
The Myth of Expert Specialization in MoEs: Why Routing Reflects Geometry, Not Necessarily Domain Expertise
Xi Wang, Soufiane Hayou, Eric Nalisnick
Mixture of Experts (MoEs) are now ubiquitous in large language models, yet the mechanisms behind their "expert specialization" remain poorly understood. We show that, since MoE rou…
Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement
Yoonsoo Nam, Nayara Fonseca, Seok Hyeong Lee +6
Dynamic feature transformation (the rich regime) does not always align with predictive performance (better representation), yet accuracy is often used as a proxy for richness, limi…
A Proof of Learning Rate Transfer under P
Soufiane Hayou
We provide the first proof of learning rate transfer with width in a linear multi-layer perceptron (MLP) parametrized with P, a neural network parameterization designed to ``ma…
Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
Nan Chen, Soledad Villar, Soufiane Hayou
Low-Rank Adaptation (LoRA) is a standard tool for parameter-efficient finetuning of large models. While it induces a small memory footprint, its training dynamics can be surprising…
PLoP: Precise LoRA Placement for Efficient Finetuning of Large Models
Soufiane Hayou, Nikhil Ghosh, Bin Yu
Low-Rank Adaptation (LoRA) is a widely used finetuning method for large models. Its small memory footprint allows practitioners to adapt large models to specific tasks at a fractio…