arxiv
PublishedMay 28, 2026 at 4:00 AM
Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses
Publisher summary· verbatim
arXiv:2605.27971v1 Announce Type: cross Abstract: When large language models are fine-tuned to generate persona- or tone-conditioned responses, their output diversity is severely limited--a failure we term Cross-Style Collapse. We trace this collapse to the cross-entropy objective, which under share
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivEDEN: A Large-Scale Corpus of Clinical Notes for Italian1darxivASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection1darxivLoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling1darxivAPPO: Agentic Procedural Policy Optimization1dThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗