5 citations · 6 across the 3 of their papers we have counts for
3 papers
cs.CL2024★ 1 cited
Linear Recency Bias During Training Improves Transformers' Fit to Reading Times
Christian Clark, Byung-Doh Oh, William Schuler
Recent psycholinguistic research has compared human reading times to surprisal estimates from language models to study the factors shaping human sentence processing difficulty. Pre…
cs.CL2024★ 5 cited
Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times
Byung-Doh Oh, Shisen Yue, William Schuler
Recent studies have shown that as Transformer-based language models become larger and are trained on very large amounts of data, the fit of their surprisal estimates to naturalisti…
cs.CL2023
Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions
Byung-Doh Oh, William Schuler
While there is much recent interest in studying why Transformer-based large language models make predictions the way they do, the complex computations performed within each layer h…