4 papers
Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures
Supantho Rakshit, Adele Goldberg, Henry Conklin
As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains.…
Meaning-infused grammar: Gradient Acceptability Shapes the Geometric Representations of Constructions in LLMs
Supantho Rakshit, Adele Goldberg
The usage-based constructionist (UCx) approach to language posits that language comprises a network of learned form-meaning pairings (constructions) whose use is largely determined…
For GPT-4 as with Humans: Information Structure Predicts Acceptability of Long-Distance Dependencies
Nicole Cuneo, Eleanor Graves, Supantho Rakshit +1
It remains debated how well any LM understands natural language or generates reliable metalinguistic judgments. Moreover, relatively little work has demonstrated that LMs can repre…
A suite of LMs comprehend puzzle statements as well as humans
Adele E Goldberg, Supantho Rakshit, Jennifer Hu +1
Recent claims suggest that large language models (LMs) underperform humans in comprehending minimally complex English statements (Dentella et al., 2024). Here, we revisit those fin…