2 papers
cs.SE2026
PELLI: Framework to effectively integrate LLMs for quality software generation
Rasmus Krebs, Somnath Mazumdar
Recent studies have revealed that when LLMs are appropriately prompted and configured, they demonstrate mixed results. Such results often meet or exceed the baseline performance. H…
cs.CL2025
Two-Stage Reasoning-Infused Learning: Improving Classification with LLM-Generated Reasoning
Mads Henrichsen, Rasmus Krebs
Standard classification models often map inputs directly to labels without explicit reasoning, potentially limiting their performance, robustness, and interpretability. This paper…