7 citations · 8 across the 4 of their papers we have counts for
7 papers · 1 filter
Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?
Atrey Desai, Sathvik Nair
For humans, filler-gap dependencies require a shared representation across different syntactic constructions. Although causal analyses suggest this may also be true for LLMs (Bogur…
Clozing the Gap: Exploring Why Language Model Surprisal Outperforms Cloze Surprisal
Sathvik Nair, Byung-Doh Oh
How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).When used as predictors of proces…
Generalizations across filler-gap dependencies in neural language models
Katherine Howitt, Sathvik Nair, Allison Dods +1
Humans develop their grammars by making structural generalizations from finite input. We ask how filler-gap dependencies, which share a structural generalization despite diverse su…
A Psycholinguistic Evaluation of Language Models' Sensitivity to Argument Roles
Eun-Kyoung Rosa Lee, Sathvik Nair, Naomi Feldman
We present a systematic evaluation of large language models' sensitivity to argument roles, i.e., who did what to whom, by replicating psycholinguistic studies on human argument ro…
Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship?
Sathvik Nair, Philip Resnik
An important assumption that comes with using LLMs on psycholinguistic data has gone unverified. LLM-based predictions are based on subword tokenization, not decomposition of words…
Evaluating Models of Robust Word Recognition with Serial Reproduction
Stephan C. Meylan, Sathvik Nair, Thomas L. Griffiths
Spoken communication occurs in a "noisy channel" characterized by high levels of environmental noise, variability within and between speakers, and lexical and syntactic ambiguity.…