arxiv
PublishedApril 1, 2026 at 4:00 AM
—neutral
The Last Fingerprint: How Markdown Training Shapes LLM Prose
Publisher summary· verbatim
arXiv:2603.27006v1 Announce Type: cross Abstract: Large language models produce em dashes at varying rates, and the observation that some models "overuse" them has become one of the most widely discussed markers of AI-generated text. Yet no mechanistic account of this pattern exists, and the paralle
Models mentioned
02Related
05- arxiv6dA Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents
- arxiv14dWorkBench Revisited: Workplace Agents Two Years On
- arxiv21dRepresentation Interventions Enable Lifelong Knowledge Memory Control in LLMs
- arxivMay 19EmoMind: Decoding Affective Captions from Human Brain fMRI
- arxivMay 11End-to-end PDDL Planning with Hardcoded and Dynamic Agents
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
arxivMulti-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling11harxivSemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests11harxivMASPRM: Multi-Agent System Process Reward Model11harxivDelving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization11hThe Bubble Brief
WEEKLYRead language models insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗