Do Language Models Exhibit Human-like Structural Priming Effects?

Jaap Jumelet, Willem Zuidema, Arabella Sinclair
6/7/2024
cs.CL

No official code found. Best implementation: jumelet/prime-factors (4 stars, last commit 2025-10-07).

Abstract

We explore which linguistic factors -- at the sentence and token level -- play an important role in influencing language model predictions, and investigate whether these are reflective of results found in humans and human corpora (Gries and Kootstra, 2017). We make use of the structural priming paradigm, where recent exposure to a structure facilitates processing of the same structure. We don't only investigate whether, but also where priming effects occur, and what factors predict them. We show that these effects can be explained via the inverse frequency effect, known in human priming, where rarer elements within a prime increase priming effects, as well as lexical dependence between prime and target. Our results provide an important piece in the puzzle of understanding how properties within their context affect structural prediction in language models.

View on arXivView PDF

Code Implementations(1)

Code for the ACL Findings paper "Do Language Models Exhibit Human-like Structural Priming Effects?"

40Shell, PythonSep 16, 20241 years ago

Similar Papers

Cite this paper

@article{jumelet2024language,
  title  = {Do Language Models Exhibit Human-like Structural Priming Effects?},
  author = {Jaap Jumelet and Willem Zuidema and Arabella Sinclair},
  year   = {2024},
  eprint = {2406.04847},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.04847v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.04847.svg)](https://codeofpaper.com/paper/2406.04847)

Discussion