10 papers
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
Peter Schneider-Kamp, Jacob Nielsen, Gianluca Barmina +2
Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and ethically sourced d…
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Gianluca Barmina, Federico Torrielli, Sven Harms +7
Large language models (LLMs) routinely face requests that should be refused, creating a trade-off between helpfulness and harm prevention. However, refusals themselves can be helpf…
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
Stine Lyngsø Beltoft, William Brach, Federico Torrielli +5
Monitoring autonomous language model agents currently relies mostly on surface behavior. But what happens when agent populations invent new languages with the goal of avoiding huma…
SommBench: Assessing Sommelier Expertise of Language Models
William Brach, Tomas Bedej, Jacob Nielsen +10
With the rapid advances of large language models, it becomes increasingly important to systematically evaluate their multilingual and multicultural capabilities. Previous cultural…
FlexMoRE: A Flexible Mixture of Rank-heterogeneous Experts for Efficient Federatedly-trained Large Language Models
Annemette Brok Pirchert, Jacob Nielsen, Mogens Henrik From +2
Recent advances in mixture-of-experts architectures have shown that individual experts models can be trained federatedly, i.e., in isolation from other experts by using a common ba…
SDUs DAISY: A Benchmark for Danish Culture
Jacob Nielsen, Stine L. Beltoft, Peter Schneider-Kamp +1
We introduce a new benchmark for Danish culture via cultural heritage, Daisy, based on the curated topics from the Danish Culture Canon 2006. For each artifact in the culture canon…