Training Language Models to Use Prolog as a Tool (2026 · 1 citation)
Language models often produce reasoning that sounds convincing but is wrong and hard to check. The authors investigate whether a small model can learn, through reinforcement learning, to offload reasoning to Prolog, whose logical derivations are explicit and inspectable. They fine-tune Qwen2.5-3B-Instruct with GRPO…
SDUs DAISY: A Benchmark for Danish Culture (2026)
Large language models are rarely tested on what they know about smaller national cultures, and until this work Danish had no standard benchmark for cultural heritage.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

Training Language Models to Use Prolog as a ToolFindings of the Association for Computational LinguisticsNiklas Mellgren, Peter Schneider-Kamp, Lukas Galke Poech2026 · 1 citation
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data ↗arXiv:2608.13517 · no summary yetPeter Schneider-Kamp et al.2026 · 1 citation
SDUs DAISY: A Benchmark for Danish CulturearXiv:2601.19930Jacob Nielsen, Stine L. Beltoft, Peter Schneider-Kamp, et al.2026

Co-authors here

1 co-author with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 2 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 31 October 2026