Louis Schiekiera

Computational Cognitive Science | Metascience | NLP & ML | Researcher Computational Modelling Lab @HumboldtUni | PhD student @FU_Berlin | #hahohe

[Louis Schiekiera @LJS_Berlin]

🚨 New preprint available! 🚨

We test how much of an LLM's internal semantic geometry can be recovered from behavior alone. Across 8 LLMs and 17.5M trials, forced-choice tasks align with hidden-state structure much better than free association.

Preprint: https://t.co/8husyo1xvi

[José A. Alonso @Jose_A_Alonso]

The agentic researcher: A practical guide to AI-assisted research in mathematics and machine learning. ~ Max Zimmer, Nico Pelleriti, Christophe Roux, Sebastian Pokutta. https://t.co/8mGyuNQkX3 #AI4Math

[Sebastian Pokutta @spokutta]

Super excited that we got this done together. Psychology x LLMs is one of the next frontiers - excited to see what else we unlock as we move forward.

#ml #ai #icml2026

[Louis Schiekiera @LJS_Berlin]

🤗 https://t.co/ztk4WYU4EH
💻 https://t.co/qye7HpowrR
✍️ https://t.co/AGXSAaQPow
See you in Seoul 👋

[Louis Schiekiera @LJS_Berlin]

New paper, accepted at ICML 2026 🎉
A 145-year-old psychology paradigm may not be the best way to probe semantic memory. We show this by running classic behavioral experiments on 8 LLMs and comparing results to their hidden states over 17.5M trials.
📄 https://t.co/BPXpjSZLFh

[Louis Schiekiera @LJS_Berlin]

Free association has dominated semantic memory research since Galton in 1879. Our results suggest it may not be the highest-fidelity instrument we have.
Thanks to co-authors @maxzimmerberlin , @chrisrx13 , @spokutta, Fritz Günther 🙏

[Max Zimmer @maxzimmerberlin]

Three papers accepted at #ICML26!

- When Does Sparsity Mitigate the Curse of Depth in LLMs
- From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs
- Lower Bounds for Frank-Wolfe on Strongly Convex Sets

arXiv below, see you in Korea 🌞

[Max Zimmer @maxzimmerberlin]

https://t.co/By1iZ4TaU4

Joint work with @LJS_Berlin, @chrisrx13, @spokutta, Fritz Günther

[Louis Schiekiera @LJS_Berlin]

Authors: Louis Schiekiera, Max Zimmer (@maxzimmerberlin), Christophe Roux (@chrisrx13), Sebastian Pokutta & Fritz Günther.

Data: https://t.co/3CosE3yqCV

[Louis Schiekiera @LJS_Berlin]

🚨 New preprint available! 🚨

We test how much of an LLM's internal semantic geometry can be recovered from behavior alone. Across 8 LLMs and 17.5M trials, forced-choice tasks align with hidden-state structure much better than free association.

Preprint: https://t.co/8husyo1xvi

[Louis Schiekiera @LJS_Berlin]

Implication: Forced choice concentrates evidence (shared candidate sets), so its behavior-derived similarity better predicts unseen hidden-state similarities even without logit access. This makes forced choice a practical probe for representation analysis.

[Max Zimmer @maxzimmerberlin]

🎉Our paper "Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?" was selected for an ORAL (top 1%) presentation at #ICML25! 🎉

arXiv: https://t.co/VkFjsaIFdx
blog: https://t.co/PdqhvtrY6o
🧵: coming soon

[Louis Schiekiera @LJS_Berlin]

Glad to be part of this initiative. PsychLing-101 will make it easier to connect and use psycholinguistic datasets across projects.

If you’re working with language processing data — join us!

[Dirk Wulff @dirkuwulff]

🚨 Inviting collaborators! 🚨

We’re launching PsychLing-101 — an open, community-driven initiative to gather psycholinguistic datasets for cross-dataset analyses and the development of psycholinguistic foundation models.

👉 To contribute, go to https://t.co/6ldJ3HyvMM

[Louis Schiekiera @LJS_Berlin]

@larsweisbrod Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems, 30.

[Louis Schiekiera @LJS_Berlin]

Excited to present our #ESCOP2025 poster on Friday 12:30 in Sheffield:

"Modeling Lexical Competition in Language Production: A Computational Approach to the Swinging Lexical Network".

Come chat about spreading activation, picture–word interference & computational modeling!

[Louis Schiekiera @LJS_Berlin]

Thanks again to @annemscheel for the open materials and to my co-author @helen_niemeyer! (4/4)

[Louis Schiekiera @LJS_Berlin]

Our study "Does Scientific Productivity Increase the Publication of Positive Results?" is now published in Collabra: Psychology! Link: https://t.co/RMg427ttN6 (1/4)

[Louis Schiekiera @LJS_Berlin]

New exploratory analyses (thanks to reviewer suggestions):
Even when analyzing ~2,000 abstracts across all SP quartiles, we still find no evidence that SP explains differences in positive result prevalence. (3/4).