Humans and language models diverge when predicting repeating text
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 58-69
Abstract
Aditya Vaidya, Javier Turek, Alexander Huth. Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL). 2023.Keywords
This publication has 19 references indexed in Scilit:
- Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers2023
- CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities2022
- Probabilistic Predictions of People Perusing: Evaluating Metrics of Language Model Performance for Psycholinguistic Modeling2020
- The human unlikeness of neural language models in next-word prediction2020
- Predictive power of word surprisal for reading times is a linear function of language model quality2018
- Critical Behavior in Physics and Probabilistic Formal LanguagesEntropy, 2017
- Verbatim and gist recall of sentences by dyslexic and non‐dyslexic adultsDyslexia, 2006
- Automatic and controlled processing in sentence recall: The role of long-term and working memoryJournal of Memory and Language, 2004
- Positive recency effect in a delayed free recallJournal of Verbal Learning and Verbal Behavior, 1973
- The effects of repetition on the short-term memory functionPsychonomic Science, 1965