6 papers
Graded strength of comparative illusions is explained by Bayesian inference
Yuhan Zhang, Erxiao Wang, Cory Shain
Like visual processing, language processing is susceptible to illusions in which people systematically misperceive stimuli. In one such case--the comparative illusion (CI), e.g., M…
Artificial Aphasias in Lesioned Language Models
Nathan Roll, Jill Kries, Laura Gwilliams +1
Aphasias, selective language impairments which can arise from brain damage, reveal the functional organization of human language by providing causal links between affected brain re…
Perturbation: A simple and efficient adversarial tracer for representation learning in language models
Joshua Rozner, Cory Shain
Linguistic representation learning in deep neural language models (LMs) has been studied for decades, for both practical and theoretical reasons. However, finding representations i…
The Text Aphasia Battery (TAB): A Clinically-Grounded Benchmark for Aphasia-Like Deficits in Language Models
Nathan Roll, Jill Kries, Flora Jin +5
Large language models (LLMs) have emerged as a candidate "model organism" for human language, offering an unprecedented opportunity to study the computational basis of linguistic d…
BabyLM's First Constructions: Causal probing provides a signal of learning
Joshua Rozner, Leonie Weissweiler, Cory Shain
Construction grammar posits that language learners acquire constructions (form-meaning pairings) from the statistics of their environment. Recent work supports this hypothesis by s…
Constructions are Revealed in Word Distributions
Joshua Rozner, Leonie Weissweiler, Kyle Mahowald +1
Construction grammar posits that constructions, or form-meaning pairings, are acquired through experience with language (the distributional learning hypothesis). But how much infor…