@LJS_Berlin profile picture
Louis Schiekiera @LJS_Berlin

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

Joined December 2018
  • Tweets 299
  • Following 527
  • Followers 93
43 Photos and videos
Pinned Tweet
Louis Schiekiera@LJS_Berlin
Feb 3
🚨 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: arxiv.org/pdf/2602.00628
1
2
3
170
Louis Schiekiera retweeted
José A. Alonso@Jose_A_Alonso
Apr 14
The agentic researcher: A practical guide to AI-assisted research in mathematics and machine learning. ~ Max Zimmer, Nico Pelleriti, Christophe Roux, Sebastian Pokutta. arxiv.org/abs/2603.15914v1 #AI4Math

The Agentic Researcher: A Practical Guide to AI-Assisted Research...

AI tools and agents are reshaping how researchers work, from proving theorems to training neural networks. Yet for many, it remains unclear how these tools fit into everyday research practice....

arxiv.org
2
9
59
2,111
Louis Schiekiera retweeted
Sebastian Pokutta@spokutta
May 4
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
May 4
Replying to @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 🙏
1
4
382
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. 📄 arxiv.org/pdf/2602.00628
1
3
6
172
more replies
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 🙏
1
2
445
🤗 huggingface.co/datasets/schi… 💻 github.com/schiekiera/llm-as… ✍️ schiekiera.github.io/blog/20… See you in Seoul 👋

schiekiera/llm-association-geometry · Datasets at Hugging Face

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

huggingface.co
25
Louis Schiekiera retweeted
Max Zimmer@maxzimmerberlin
May 1
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 🌞
1
2
16
946
Louis Schiekiera retweeted
Max Zimmer@maxzimmerberlin
May 1
arxiv.org/abs/2602.00628 Joint work with @LJS_Berlin, @chrisrx13, @spokutta, Fritz Günther

From Associations to Activations: Comparing Behavioral and...

We investigate the extent to which an LLM's hidden-state geometry can be recovered from its behavior in psycholinguistic experiments. Across eight instruction-tuned transformer models, we run two...

arxiv.org
1
2
2
126
🚨 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: arxiv.org/pdf/2602.00628
1
2
3
170
more replies
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.
1
23
Authors: Louis Schiekiera, Max Zimmer (@maxzimmerberlin), Christophe Roux (@chrisrx13), Sebastian Pokutta & Fritz Günther. Data: huggingface.co/datasets/schi…

schiekiera/llm-association-geometry · Datasets at Hugging Face

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

huggingface.co
46
Louis Schiekiera retweeted
Max Zimmer@maxzimmerberlin
10 Jun 2025
🎉Our paper "Neural Discovery in Mathematics: Do Machines Dream of Colored Planes?" was selected for an ORAL (top 1%) presentation at #ICML25! 🎉 arXiv: arxiv.org/abs/2501.18527 blog: maxzimmer.org/blog/2025/neur… 🧵: coming soon
1
3
7
562
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
12 Nov 2025
🚨 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 github.com/Data-X01/PsychLin…
1
27
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!
1
154
Our study "Does Scientific Productivity Increase the Publication of Positive Results?" is now published in Collabra: Psychology! Link: doi.org/10.1525/collabra.137… (1/4)
1
1
3
330
more replies
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).
1
41
Thanks again to @annemscheel for the open materials and to my co-author @helen_niemeyer! (4/4)
34
Load more