19 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…
Training Language Models to Use Prolog as a Tool
Niklas Mellgren, Peter Schneider-Kamp, Lukas Galke Poech
Language models frequently produce plausible yet incorrect reasoning traces that are difficult to verify. We investigate fine-tuning models to use Prolog as an external symbolic re…
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
Filippo Tonini, Federico Torrielli, Anton Danholt Lautrup +3
As AI systems built from multiple language-model agents become more common, they are increasingly used to make decisions together: discussing, negotiating, and acting on shared tas…
BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling
Gianluca Barmina, Annemette Broch Pirchert, Andrea Blasi Núñez +2
As deep learning models scale, managing, inspecting, and modifying large checkpoints has become increasingly challenging. Researchers often need to alter model weights for layer re…
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…
Disjoint Generation of Synthetic Data
Anton Danholt Lautrup, Muhammad Rajabinasab, Tobias Hyrup +2
We propose a new framework for generating tabular synthetic datasets via disjoint generative models. In this paradigm, a dataset is partitioned into disjoint subsets that are suppl…