Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Dual-objective Language Models: Training Efficiency Without Overfitting
David Samuel, Lucas Georges Gabriel Charpentier
This paper combines autoregressive and masked-diffusion training objectives without any architectural modifications, resulting in flexible language models that outperform single-ob…
cs.CL2026
Fluent Alignment with Disfluent Judges: Post-training for Lower-resource Languages
David Samuel, Lilja Ãvrelid, Erik Velldal +1
We propose a post-training method for lower-resource languages that preserves the fluency of language models even when aligned by disfluent reward models. Preference optimization i…