Language models align with human judgments on key grammatical constructions
Abstract
Do large language models (LLMs) make human-like linguistic generalizations? Dentella et al. (2023) ("DGL") prompt several LLMs ("Is the following sentence grammatically correct in English?") to elicit grammaticality judgments of 80 English sentences, concluding that LLMs demonstrate a "yes-response bias" and a "failure to distinguish grammatical from ungrammatical sentences". We re-evaluate LLM performance using well-established practices and find that DGL's data in fact provide evidence for just how well LLMs capture human behaviors. Models not only achieve high accuracy overall, but also capture fine-grained variation in human linguistic judgments.
Cite
@article{arxiv.2402.01676,
title = {Language models align with human judgments on key grammatical constructions},
author = {Jennifer Hu and Kyle Mahowald and Gary Lupyan and Anna Ivanova and Roger Levy},
journal= {arXiv preprint arXiv:2402.01676},
year = {2024}
}
Comments
Published in PNAS at https://www.pnas.org/doi/10.1073/pnas.2400917121 as response to Dentella et al. (2023)