SDUs DAISY: A Benchmark for Danish Culture
Nielsen, Jacob; Beltoft, Stine L.; Schneider-Kamp, Peter; Poech, Lukas Galke
Publication link · arXiv
Publications
Selected OdenseNLP publications.
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
Barmina, Gianluca; Schneider-Kamp, Peter; Poech, Lukas Galke
Publication link · arXiv
The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment
Brach, William; Torrielli, Federico; Beltoft, Stine Lyngso; Pirchert, Annemette Brok; Schneider-Kamp, Peter; Poech, Lukas Galke
Publication link · arXiv
Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals
Torrielli, Federico; Schneider-Kamp, Peter; Poech, Lukas Galke
Publication link · arXiv
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
Beltoft, Stine Lyngso; Brach, William; Torrielli, Federico; Nielsen, Jacob; Pirchert, Annemette Brok; Tonini, Filippo; Schneider-Kamp, Peter; Poech, Lukas Galke
Publication link · arXiv
FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models
Pirchert, Annemette Brok; Nielsen, Jacob; From, Mogens Henrik; Poech, Lukas Galke; Schneider-Kamp, Peter
Publication link · arXiv
MLDataForge: Accelerating Large-Scale Dataset Preprocessing and Access for Multimodal Foundation Model Training
Blasi Nunez, Andrea; Galke, Lukas Paul Achatius; Schneider-Kamp, Peter
Publication link · ACL Anthology
Not Everything That Counts Can Be Counted: A Case for Safe Qualitative AI
Beltoft, Stine; Galke, Lukas
Publication link · arXiv
Chain of Summaries: Summarization Through Iterative Questioning
Brach, William; Kostal, Kristian; Poech, Lukas Galke
Publication link · arXiv
Isolating Culture Neurons in Multilingual Large Language Models
Namazifard, Danial; Poech, Lukas Galke
Publication link · ACL Anthology
DeToNATION: Decoupled Torch Network-Aware Training on Interlinked Online Nodes
From, Mogens Henrik; Nielsen, Jacob; Poech, Lukas Galke; Schneider-Kamp, Peter
Publication link · arXiv
Training Language Models to Use Prolog as a Tool
Mellgren, Niklas; Schneider-Kamp, Peter; Poech, Lukas Galke
Publication link · arXiv
Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
Nielsen, Jacob; Schneider-Kamp, Peter; Poech, Lukas Galke
Publication link · ACL Anthology
Super-additive Cooperation in Language Model Agents
Tonini, Filippo; Galke, Lukas
Publication link · arXiv
DaLA: Danish Linguistic Acceptability Evaluation Guided by Real World Errors
Barmina, Gianluca; Norman, Nathalie Carmen Hau; Schneider-Kamp, Peter; Poech, Lukas Galke
Publication link · arXiv
When are 1.58 bits enough? A Bottom-up Exploration of BitNet Quantization
Nielsen, Jacob; Poech, Lukas Galke; Schneider-Kamp, Peter
Publication link · arXiv
BitNet B1.58 Reloaded: State-of-the-Art Performance Also on Smaller Networks
Nielsen, Jacob; Schneider-Kamp, Peter
Publication link · Springer