Research
Agnostic Language Identification and Generation
arXiv:2601.23258v2 Announce Type: replace-cross Abstract: Recent works on language identification and generation have established tight statistical rates at which these tasks can be achieved. These wo
arXiv:2601.23258v2 Announce Type: replace-cross Abstract: Recent works on language identification and generation have established tight statistical rates at which these tasks can be achieved. These works typically operate under a strong realizability assumption: that the input data is drawn from an unknown distribution necessarily supported on some language in a given collection. In this work, we relax this assumption of realizability entirely, and impose no restrictions on the distribution of the input data. We propose objectives to study both language identification and generation in this more general "agnostic" setup. Across both problems, we obtain novel interesting characterizations and nearly tight rates.
Related
- CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language
- Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow
- Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?
Source: arXiv cs.AI | 2026-04-23