Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
Paper
•
2601.02989
•
Published
•
4
Ali Nafisi
safinal
ErfanMoosaviMonazzah's profile picture
sadeghsamani's profile picture
Saleh-Aslani's profile picture
·
AI & ML interests
NLP, Multimodal Models, Trustworthiness, Neuro-Symbolic AI, Reinforcement Learning
Recent Activity
authored
a paper
2 days ago
Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
submitted
a paper
2 days ago
Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy
Organizations
authored
a
paper
2 days ago
submitted
a
paper
to Daily Papers
2 days ago