arxiv
PublishedApril 24, 2026 at 4:00 AM
—neutral
Language as a Latent Variable for Reasoning Optimization
Publisher summary· verbatim
arXiv:2604.21593v1 Announce Type: new Abstract: As LLMs reduce English-centric bias, a surprising trend emerges: non-English responses sometimes outperform English on reasoning tasks. We hypothesize that language functions as a latent variable that structurally modulates the model's internal inferen
Discussion
No replies yet. Be first.
Originally published on arxiv ↗