works on
deep equilibrium models 1gradient starvation 1implicit layers 1model diagnostics 1physics-informed networks 1reasoning benchmarks 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement

Aoxin Ni

Large language models (LLMs) achieve strong results on mathematical reasoning benchmarks yet remain unreliable on elementary numerical tasks, including magnitude comparison, large-…