AI RESEARCH
Language as a Latent Variable for Reasoning Optimization
arXiv CS.CL
•
ArXi:2604.21593v1 Announce Type: new 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 inference pathways, rather than merely serving as an output medium. To test this, we conducted a Polyglot Thinking Experiment, in which models were prompted to solve identical problems under language-constrained and language-unconstrained conditions.