2 papers
cs.LG2024
Natural Mitigation of Catastrophic Interference: Continual Learning in Power-Law Learning Environments
Atith Gandhi, Raj Sanjay Shah, Vijay Marupudi +1
Neural networks often suffer from catastrophic interference (CI): performance on previously learned tasks drops off significantly when learning a new task. This contrasts strongly…
cs.AI2023
Human Behavioral Benchmarking: Numeric Magnitude Comparison Effects in Large Language Models
Raj Sanjay Shah, Vijay Marupudi, Reba Koenen +2
Large Language Models (LLMs) do not differentially represent numbers, which are pervasive in text. In contrast, neuroscience research has identified distinct neural representations…