iiinova — where your digital self keeps evolving

Reposted by Sam Boeve

In-Mind: Psychology for You! @in-mindmagazine.bsky.social · 29/12/2025

📊 𝗛𝗶𝗴𝗵𝗹𝗶𝗴𝗵𝘁𝘀 𝗳𝗿𝗼𝗺 𝟮𝟬𝟮𝟱: 📑 33 articles were published on In-Mind.  📌 The most interacted article on Bluesky was “Language models: A new perspective on language and cognition” by @boevesam.bsky.social. 👉 Read the post here again: bsky.app/profile/in-m...

bsky.app

In-Mind: Psychology for You! (@in-mindmagazine.bsky.social)

🔔 𝗡𝗲𝘄 𝗮𝗿𝘁𝗶𝗰𝗹𝗲: 𝗔 𝗻𝗲𝘄 𝗽𝗲𝗿𝘀𝗽𝗲𝗰𝘁𝗶𝘃𝗲 𝗼𝗻 𝗹𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗮𝗻𝗱 𝗰𝗼𝗴𝗻𝗶𝘁𝗶𝗼𝗻 🔔 How can computers help us understand language learning? 🤖 From readability scores to…

111

Reposted by Sam Boeve

In-Mind: Psychology for You! @in-mindmagazine.bsky.social · 30/12/2025

📑 𝗪𝗵𝗮𝘁 𝘄𝗲 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱 In 2025, we published 33 articles and 12 blog posts. 📌 The most interacted article on Bluesky was “Language models: A new perspective on language and cognition” by @boevesam.bsky.social 👉 Read it again here:  bsky.app/profile/in-m...

131

Reposted by Sam Boeve

BogaertsLab @bogaertslab.bsky.social · 02/09/2025

👁️ 📖 👁️ @boevesam.bsky.social made this interactive visualisation to get a feeling for word predictability: 🔗 wordpredictabilityvisualized.vercel.app Curious how these predictability indices were obtained? Find out in our new paper! 🔗 doi.org/10.3758/s134... #Reading #LargeLanguageModels #MECO

031

Sam Boeve @boevesam.bsky.social · 02/09/2025

Want to explore word predictability yourself on a sample of each corpus used in this work, check out this app: wordpredictabilityvisualized.vercel.app

wordpredictabilityvisualized.vercel.app

Word Predictability Visualization App

000

Sam Boeve @boevesam.bsky.social · 02/09/2025

Modelling reading times in Dutch?: gpt2-small-dutch (huggingface.co/GroNLP/gpt2-...) or gpt2-medium-dutch-embeddings (huggingface.co/GroNLP/gpt2-...) are great options.

huggingface.co

GroNLP/gpt2-small-dutch · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

100

Sam Boeve @boevesam.bsky.social · 02/09/2025

3. Predictability effects are also logarithmic in Dutch, corroborating effects found in English (= linear effect of surprisal): For very unpredictable words, a decrease in predictability has a much larger slowing-down effect on reading times than the same decrease for highly predictable words.

100

Sam Boeve @boevesam.bsky.social · 02/09/2025

2. Language-specific models are generally better than multilingual ones (multilingual models are shown in blue in the figure below).

100

Sam Boeve @boevesam.bsky.social · 02/09/2025

Key findings 📝 1. Smaller Dutch models often predict reading times better (= inverse scaling trend) ~ in line with evidence of English models. But, with more context (in a book reading corpus), larger models catch up.

100

Sam Boeve @boevesam.bsky.social · 02/09/2025

Large language models are powerful tools for psycholinguistic research. But, most evidence so far is limited to English. How well do Dutch open-source language models fit reading times using their word predictability estimates?

100

Reposted by Sam Boeve

German Word Nerd Network @gewonnofficial.bsky.social · 12/03/2025

✨Playback at #teap2025 (Part 1) Thanks to the amazing speakers and the audience for the successful symposium on #languagemodels in #psycholinguistics! Katharina Menn, @hannawoloszyn.bsky.social, @boevesam.bsky.social, Marco Marelli, Fritz Günther, @benjamingagl.bsky.social

081

Reposted by Sam Boeve

BogaertsLab @bogaertslab.bsky.social · 11/03/2025

Proud PI! 👏 On #TeaP2025 two lab members presented their work: Haoyu Zhou in the symposium #StatisticalLearning and its Role in #Language and #Reading acquisition. @boevesam.bsky.social in the symposium From Babies to Semantics: Leveraging #LanguageModels for #Psycholinguistic Research.

185

Sam Boeve @boevesam.bsky.social · 19/12/2024

Overall, our results provide a psychometric leaderboard of Dutch large language models, ideal for researchers interested in effects of predictability in Dutch. Check out our full dataset and code here: osf.io/wr4qf/

osf.io

A Systematic Evaluation of Dutch Large Language Models’ Surprisal Estimates in Sentence, Paragraph, and Book Reading

A psychometric evaluation of Dutch large language models. Hosted on the Open Science Framework

000

Sam Boeve @boevesam.bsky.social · 19/12/2024

Finally, we found a linear link between surprisal and reading times except for the GECO corpus where a non-linear link between surprisal and reading times fitted the data best. A challenge to the notion of an universal linear effect of surprisal.

100

Sam Boeve @boevesam.bsky.social · 19/12/2024

Second, smaller Dutch models showed a better fit to reading times than the largest models, replicating the inverse scaling trend seen in English. However, this effect varied depending on the corpus used.

100

Sam Boeve @boevesam.bsky.social · 19/12/2024

First, across three eye-tracking corpora, we found that in each case, a Dutch LLMs' surprisal estimates outperformed the multilingual model (mGPT) and the N-gram model in predicting reading times.

100

Sam Boeve @boevesam.bsky.social · 19/12/2024

3. Does surprisal still show linear link with reading times when estimated with a Dutch-specific language model as opposed to a multilingual model?

110

Sam Boeve @boevesam.bsky.social · 19/12/2024

2. Do these Dutch-specific LLMs show a similar inverse scaling trend as English models? That is, do the smaller transformer models' surprisal estimates account better for reading times than those of the very large models?

100

Sam Boeve @boevesam.bsky.social · 19/12/2024

1. What is the best computational method for estimating word predictability in Dutch? We compare 14 Dutch large language models (LLMs), a multilingual model (mGPT) and an N-gram model in their ability of explaining reading times.

100

Sam Boeve @boevesam.bsky.social · 19/12/2024

The effect of word predictability on reading times is well established for English but not so much for Dutch. We adressed this and asked three questions:

100

Sam Boeve @boevesam.bsky.social · 19/12/2024

Ending the year on a high note with the submission of a new preprint: A Systematic Evaluation of Dutch Large Language Models’ Surprisal Estimates in Sentence, Paragraph, and Book Reading Preprint: dx.doi.org/10.13140/RG.... OSF: osf.io/wr4qf/

osf.io

A Systematic Evaluation of Dutch Large Language Models’ Surprisal Estimates in Sentence, Paragraph, and Book Reading

A psychometric evaluation of Dutch large language models. Hosted on the Open Science Framework

130