# Agnostic Language Identification and Generation

arXiv: https://arxiv.org/abs/2601.23258 · HTML: https://mlsanity.com/paper/2601.23258/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 10 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 7 of 7)

- [A Theory of Universal Learning](https://mlsanity.com/paper/2011.04483/) (2020)
- [Language Generation in the Limit](https://mlsanity.com/paper/2404.06757/) (2024)
- [Generation through the lens of learning theory](https://mlsanity.com/paper/2410.13714/) (2024)
- [Exploring Facets of Language Generation in the Limit](https://mlsanity.com/paper/2411.15364/) (2024)
- [Generation from Noisy Examples](https://mlsanity.com/paper/2501.04179/) (2025)
- [Language Generation in the Limit: Noise, Loss, and Feedback](https://mlsanity.com/paper/2507.15319/) (2025)
- [Language Generation with Infinite Contamination](https://mlsanity.com/paper/2511.07417/) (2025)

## Built on by (most cited first, 4 of 4)

- [Contrastive Identification and Generation in the Limit](https://mlsanity.com/paper/2605.06211/) (2026)
- [On the Price of Privacy for Language Identification and Generation](https://mlsanity.com/paper/2604.07238/) (2026)
- [Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit](https://mlsanity.com/paper/2606.14688/) (2026)
- [Reconciling Universal and Uniform Learning with Q-Aggregation](https://mlsanity.com/paper/2609.05041/) (2026)

## Abstract (arXiv)

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.