iiinova — where your digital self keeps evolving

Nina Nusbaumer @nina-nusbaumer.bsky.social · 22/09/2026

New paper🎉 With Nazanin Shafiabadi & Olivier Bonami, we ask how predictable French noun gender is from form alone. LSTMs (no suffix info given) reach ~90% accuracy and converge exactly on suffix boundaries, suggesting morphology drives this predictability. 🔗 www.peren-revues.fr/lexique/2262

010

Reposted by Nina Nusbaumer

Caroline Rowland @carorowland.bsky.social · 27/08/2026

This is the perfect title for the final lecture in the Analytical Connectionism school. www.analytical-connectionism.net/school/2026/

Title slide of a presentation. Title: Are LLMs relevant from studying language development in humans?
Author: Afra Alishahi
Affiliation: Center for Cognitive Science and AI
Tilburg University, the Netherlands

072

Nina Nusbaumer @nina-nusbaumer.bsky.social · 19/12/2025

Presented our new **reading time benchmark for Human Sentence Processing modeling** at the Computational Psycholinguistics Meeting in Utrecht 🧠 Expected to be released in open-source in the upcoming months. Keep an eye out! 👀

040

Reposted by Nina Nusbaumer

Marianne de Heer Kloots @mdhk.net · 19/12/2025

Cool posters from day 2! @sashakenjeeva.bsky.social openreview.net/forum?id=Vtd... github.com/markvandenho... openreview.net/forum?id=rX3... @nina-nusbaumer.bsky.social openreview.net/forum?id=GRz... www.ru.nl/personen/sui... openreview.net/forum?id=NcJ...

Poster title: Does multimodal pre-activation influence linguistic expectations in LLMs and humans?

Authors: Sasha Kenjeeva, Giovanni Cassani, Noortje Venhuizen, Afra Alishahi

Poster title: Generalizing Without Evidence: How Transformer Models Infer Syntactic Rules From Sparse Input

Authors: Mark van den Hoorn, Raquel G. Alhama

Poster title: Dependency Length, Syntactic Complexity & Memory: A Reading Time Benchmark for Sentence Processing Modeling

Authors: Nina Nusbaumer, Corentin Bel, Iria de-Dios-Flores, Guillaume Wisniewski, Benoit Crabbé

Poster title:
The success of Neural Language Models on syntactic island effects is not universal: strong wh-island sensitivity in English but not in Dutch

Authors: Michelle Suijkerbuijk, Naomi Tachikawa Shapiro, Peter de Swart, Stefan L. Frank

141

Reposted by Nina Nusbaumer

Cameron Buckner @cameronbuckner.bsky.social · 15/10/2025

Another banger from @tallinzen.bsky.social . Also fits with some of the criticisms of Centaur and my faculty-based approach generally; if you want LLMs to model human cognition, give them more architecture akin to human faculty psychology like long and short-term memory. arxiv.org/abs/2510.05141

arxiv.org

To model human linguistic prediction, make LLMs less superhuman

When people listen to or read a sentence, they actively make predictions about upcoming words: words that are less predictable are generally read more slowly than predictable ones. The success of larg...

1236

Nina Nusbaumer @nina-nusbaumer.bsky.social · 02/10/2025

First paper is out! Had so much fun presenting it in Marseille last July 🇨🇵 We explore how transformers handle compositionality by exploring the representations of the idiomatic and literal meaning of the same noun phrase (e.g. "silver spoon"). aclanthology.org/2025.jeptaln...

051