Sign in

Lukas Galke

@lukasgalke.bsky.social
150 followers 367 following 10 posts

Assistant Professor @SDU tracing connectionist mechanisms. lgalke.github.io

PostsRepliesMedia
Reposted by Lukas Galke
Danial Namazifard @namazifard.bsky.social · 05/09/2025
🚀 Excited to share our latest work, "Isolating Culture Neurons in Multilingual Large Language Models". 💻 Data & code: github.com/namazifard/C... 📄 Preprint: arxiv.org/abs/2508.02241
arxiv.org
Isolating Culture Neurons in Multilingual Large Language Models
Language and culture are deeply intertwined, yet it is so far unclear how and where multilingual large language models encode culture. Here, we extend upon an established methodology for identifying l...
162
Reposted by Lukas Galke
Arianna Bisazza @arianna-bis.bsky.social · 18/04/2025
RAG is a powerful way to improve LLMs' answering abilities across many languages. But how do LLMs deal with multilingual contexts? Do they answer consistently when the retrieved info is provided to them in different languages? Joint work w/ @jiruiqi.bsky.social & Raquel_Fernández See thread! ⤵️
062
Reposted by Lukas Galke
Ansgar Scherp @ansgarscherp.bsky.social · 20/02/2025
🗞️ A simple trick improves embedding retrieval performance even without further training. ZCA whitening increases isotropy of the embedding space and thereby helps retrieval Paper by Andor Diera and with @lukasgalke.bsky.social at ESANN 2025. Preprint: arxiv.org/abs/2411.17538
arxiv.org
Isotropy Matters: Soft-ZCA Whitening of Embeddings for Semantic Code Search
Low isotropy in an embedding space impairs performance on tasks involving semantic inference. Our study investigates the impact of isotropy on semantic code search performance and explores post-proces...
011
Reposted by Lukas Galke
Kristian Kersting @kerstingaiml.bsky.social · 24/01/2025
Thrilled to share our #ICLR2025 work on Meta-Causal States! 🌟 Causal graphs evolve with dynamic systems & agent actions. We show how to cluster causal models by qualitative behavior, revealing hidden dynamics & emergent relationships 🚀 #Causality #ML arxiv.org/abs/2410.13054
0126
Reposted by Lukas Galke
Max Planck Institute for Psycholinguistics @mpi-nl.bsky.social · 03/01/2025
Deep neural networks and humans both benefit from compositional language structure. New paper by @lukasgalke.bsky.social, Yoav Ram, and @limorraviv.bsky.social. doi.org/10.1038/s414....
doi.org
Deep neural networks and humans both benefit from compositional language structure - Nature Communications
This study demonstrates that deep neural networks, like humans, show a learnability advantage when trained on languages with more structured linguistic input, resulting in closer alignment with human ...
175
Lukas Galke @lukasgalke.bsky.social · 30/12/2024
🔥 Now finally out in Nature Communications: Deep neural networks and humans both benefit from compositional structure with Yoav Ram and @limorraviv.bsky.social Paper link right away: rdcu.be/d5f2e 🧵⬇️
rdcu.be
Deep neural networks and humans both benefit from compositional language structure
Nature Communications - This study demonstrates that deep neural networks, like humans, show a learnability advantage when trained on languages with more structured linguistic input, resulting in...
1123
Lukas Galke @lukasgalke.bsky.social · 17/12/2024
Two more days left to apply for PhD positions on training multilingual language models at the Centre for Machine Learning in the Department of Mathematics and Computer Science (IMADA), University of Southern Denmark (SDU). tinyurl.com/dfm2025phd Application deadline: Dec 19, 2024
tinyurl.com
Several PhD scholarships in Artificial Intelligence
Application deadline: 19 December 2024 at 23:59 hours local Danish time
021
Reposted by Lukas Galke
Yoav Goldberg @yoavgo.bsky.social · 24/11/2024
tell me about LLMs tool use best practices. I know the high level, and want to learn about implementation/prompting details, e.g.: - how do you best feed in the tool specs or DSL to the LLM? - how do you ask it to indicate a tool use (which wrapper / indicator) - how do you ask for nested calls etc
9384
Lukas Galke @lukasgalke.bsky.social · 22/11/2024
We have some openings for PhD/Postdoc positions on multilingual language modeling at SDU's Centre for Machine Learning, Denmark. Topics go down to the core of pre-training and instruction tuning and adjacent topics such as efficient language modeling. Please consider to apply :)
100
Reposted by Lukas Galke
c4ml.bsky.social @c4ml.bsky.social · 22/11/2024
Research positions on LLMs and available at the SDU Centre for ML: tinyurl.com/dfm2025phd tinyurl.com/dfm2025postdoc
tinyurl.com
Several PhD scholarships in Artificial Intelligence
Application deadline: 19 December 2024 at 23:59 hours local Danish time
011
Lukas Galke @lukasgalke.bsky.social · 19/11/2024
I'm Lukas, working on machine learning and natural language processing. I'm particularly interested in interpretability of language models, efficient language models, continual learning, ood generalization, and machine communication. I hope to find a community like the ex-twitter ML community here.
160