Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?

23 December 2022

Papers citing "Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?"

50 / 50 papers shown

Title
Model Connectomes: A Generational Approach to Data-Efficient Language Models Klemen Kotar Greta Tuckute 49 0 0 29 Apr 2025
Signatures of human-like processing in Transformer forward passes Jennifer Hu Michael A. Lepori Michael Franke AI4CE 156 0 0 18 Apr 2025
Generative Linguistics, Large Language Models, and the Social Nature of Scientific Success Sophie Hao ELM AI4CE 54 0 0 25 Mar 2025
Strategic resource allocation in memory encoding: An efficiency principle shaping language processing Weijie Xu Richard Futrell 55 1 0 18 Mar 2025
From Language to Cognition: How LLMs Outgrow the Human Language Network Badr AlKhamissi Greta Tuckute Yingtian Tang Taha Binhuraib Antoine Bosselut Martin Schrimpf ALM 154 1 0 03 Mar 2025
Language Models Grow Less Humanlike beyond Phase Transition Tatsuya Aoyama Ethan Wilcox 46 1 0 26 Feb 2025
Anything Goes? A Crosslinguistic Study of (Im)possible Language Learning in LMs Xiulin Yang Tatsuya Aoyama Yuekun Yao Ethan Wilcox 50 1 0 26 Feb 2025
Eye Tracking Based Cognitive Evaluation of Automatic Readability Assessment Measures Keren Gruteke Klein Shachar Frenkel Omer Shubi Yevgeni Berzak 43 0 0 16 Feb 2025
Large Language Models Are Human-Like Internally Tatsuki Kuribayashi Yohei Oseki Souhaib Ben Taieb Kentaro Inui Timothy Baldwin 71 4 0 03 Feb 2025
Learning to Write Rationally: How Information Is Distributed in Non-Native Speakers' Essays Zixin Tang Janet G. van Hell 29 0 0 05 Nov 2024
What Goes Into a LM Acceptability Judgment? Rethinking the Impact of Frequency and Length Lindia Tjuatja Graham Neubig Tal Linzen Sophie Hao 44 1 0 04 Nov 2024
Towards a Similarity-adjusted Surprisal Theory Clara Meister Mario Giulianelli Tiago Pimentel 32 3 0 23 Oct 2024
A Psycholinguistic Evaluation of Language Models' Sensitivity to Argument Roles Eun-Kyoung Rosa Lee Sathvik Nair Naomi Feldman 62 4 0 21 Oct 2024
Reverse-Engineering the Reader Samuel Kiegeland Ethan Gotlieb Wilcox Afra Amini David Robert Reich Ryan Cotterell 23 0 0 16 Oct 2024
Large-scale cloze evaluation reveals that token prediction tasks are neither lexically nor semantically aligned Cassandra L. Jacobs Loïc Grobol Alvin Tsang 21 0 0 15 Oct 2024
The Roles of Contextual Semantic Relevance Metrics in Human Visual Processing Kun Sun Rong Wang VLM 30 0 0 13 Oct 2024
Linear Recency Bias During Training Improves Transformers' Fit to Reading Times Christian Clark Byung-Doh Oh William Schuler 33 3 0 17 Sep 2024
Thesis proposal: Are We Losing Textual Diversity to Natural Language Processing? Josef Jon 31 0 0 15 Sep 2024
On the Role of Context in Reading Time Prediction Andreas Opedal Eleanor Chodroff Ryan Cotterell Ethan Gotlieb Wilcox 33 7 0 12 Sep 2024
Brain-Like Language Processing via a Shallow Untrained Multihead Attention Network Badr AlKhamissi Greta Tuckute Antoine Bosselut Martin Schrimpf 76 6 0 21 Jun 2024
How to Compute the Probability of a Word Tiago Pimentel Clara Meister 28 14 0 20 Jun 2024
SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking Zhuang Li Yuncheng Hua Thuy-Trang Vu Haolan Zhan Lizhen Qu Gholamreza Haffari 54 2 0 16 Jun 2024
Leading Whitespaces of Language Models' Subword Vocabulary Poses a Confound for Calculating Word Probabilities Byung-Doh Oh William Schuler 27 14 0 16 Jun 2024
Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences Patrick Haller Lena S. Bolliger Lena Ann Jäger 39 1 0 07 Jun 2024
Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence Abhinav Patil Jaap Jumelet Yu Ying Chiu Andy Lapastora Peter Shen Lexie Wang Clevis Willrich Shane Steinert-Threlkeld 35 13 0 24 May 2024
Revenge of the Fallen? Recurrent Models Match Transformers at Predicting Human Language Comprehension Metrics J. Michaelov Catherine Arnett Benjamin Bergen 34 3 0 30 Apr 2024
Computational Sentence-level Metrics Predicting Human Sentence Comprehension Kun Sun Rong Wang 46 0 0 23 Mar 2024
Emergent Word Order Universals from Cognitively-Motivated Language Models Tatsuki Kuribayashi Ryo Ueda Ryosuke Yoshida Yohei Oseki Ted Briscoe Timothy Baldwin 38 2 0 19 Feb 2024
Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times Byung-Doh Oh Shisen Yue William Schuler 53 14 0 03 Feb 2024
$Describing Images $\textit{Fast and Slow}$: Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes$ Describing Images $\textit{Fast and Slow}$ : Quantifying and Predicting the Variation in Human Signals during Visuo-Linguistic Processes Ece Takmaz Sandro Pezzelle Raquel Fernández 24 1 0 02 Feb 2024
Multipath parsing in the brain Berta Franzluebbers Donald Dunagan Milovs Stanojević Jan Buys John T. Hale 16 0 0 31 Jan 2024
Instruction-tuning Aligns LLMs to the Human Brain Khai Loong Aw Syrielle Montariol Badr AlKhamissi Martin Schrimpf Antoine Bosselut 33 18 0 01 Dec 2023
Attribution and Alignment: Effects of Local Context Repetition on Utterance Production and Comprehension in Dialogue Aron Molnar Jaap Jumelet Mario Giulianelli Arabella J. Sinclair 30 2 0 21 Nov 2023
Temperature-scaling surprisal estimates improve fit to human reading times -- but does it do so for the "right reasons"? Tong Liu Iza vSkrjanec Vera Demberg 48 5 0 15 Nov 2023
Structural Priming Demonstrates Abstract Grammatical Representations in Multilingual Language Models J. Michaelov Catherine Arnett Tyler A. Chang Benjamin Bergen 36 12 0 15 Nov 2023
Psychometric Predictive Power of Large Language Models Tatsuki Kuribayashi Yohei Oseki Timothy Baldwin LM&MA 26 3 0 13 Nov 2023
Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures Julius Steuer Marius Mosbach Dietrich Klakow 27 10 0 08 Nov 2023
Roles of Scaling and Instruction Tuning in Language Perception: Model vs. Human Attention Changjiang Gao Shujian Huang Jixing Li Jiajun Chen LRM ALM 39 6 0 29 Oct 2023
Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship? Sathvik Nair Philip Resnik 27 10 0 26 Oct 2023
When Language Models Fall in Love: Animacy Processing in Transformer Language Models Michael Hanna Yonatan Belinkov Sandro Pezzelle 27 11 0 23 Oct 2023
Information Value: Measuring Utterance Predictability as Distance from Plausible Alternatives Mario Giulianelli Sarenne Wallbridge Raquel Fernández 25 13 0 20 Oct 2023
Humans and language models diverge when predicting repeating text Aditya R. Vaidya Javier S. Turek Alexander G. Huth 19 6 0 10 Oct 2023
Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability Tyler A. Chang Z. Tu Benjamin Bergen 32 11 0 29 Aug 2023
Testing the Predictions of Surprisal Theory in 11 Languages Ethan Gotlieb Wilcox Tiago Pimentel Clara Meister Ryan Cotterell R. Levy LRM 46 63 0 07 Jul 2023
Investigating the Utility of Surprisal from Large Language Models for Speech Synthesis Prosody Sofoklis Kakouros J. Šimko M. Vainio Antti Suni 12 5 0 16 Jun 2023
Transformer-Based Language Model Surprisal Predicts Human Reading Times Best with About Two Billion Training Tokens Byung-Doh Oh William Schuler 42 25 0 22 Apr 2023
On the Effect of Anticipation on Reading Times Tiago Pimentel Clara Meister Ethan Gotlieb Wilcox R. Levy Ryan Cotterell 39 18 0 25 Nov 2022
Syntactic Surprisal From Neural Models Predicts, But Underestimates, Human Processing Difficulty From Syntactic Ambiguities Suhas Arehalli Brian Dillon Tal Linzen 34 36 0 21 Oct 2022
Context Limitations Make Neural Language Models More Human-Like Tatsuki Kuribayashi Yohei Oseki Ana Brassard Kentaro Inui 44 29 0 23 May 2022
Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention S. Ryu Richard L. Lewis 33 25 0 26 Apr 2021