# A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse

arXiv: https://arxiv.org/abs/2605.11302 · HTML: https://mlsanity.com/paper/2605.11302/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 18 of 18)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Calibrated Language Models Must Hallucinate](https://mlsanity.com/paper/2311.14648/) (2023)
- [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)
- [Density Measures for Language Generation](https://mlsanity.com/paper/2504.14370/) (2025)
- [Generation from Noisy Examples](https://mlsanity.com/paper/2501.04179/) (2025)
- [Representative Language Generation](https://mlsanity.com/paper/2505.21819/) (2025)
- [On Union-Closedness of Language Generation](https://mlsanity.com/paper/2506.18642/) (2025)
- [Language Generation in the Limit: Noise, Loss, and Feedback](https://mlsanity.com/paper/2507.15319/) (2025)
- [(Im)possibility of Automated Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2504.17004/) (2025)
- [On Characterizations for Language Generation: Interplay of Hallucinations, Breadth, and Stability](https://mlsanity.com/paper/2412.18530/) (2024)
- [Language Generation and Identification From Partial Enumeration: Tight Density Bounds and Topological Characterizations](https://mlsanity.com/paper/2511.05295/) (2025)
- [Pareto-optimal Non-uniform Language Generation](https://mlsanity.com/paper/2510.02795/) (2025)
- [EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents](https://mlsanity.com/paper/2412.13549/) (2024)

## Built on by (most cited first, 3 of 3)

- [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)
- [Hallucination Rates in Language Generation](https://mlsanity.com/paper/2607.23361/) (2026)
- [GenLimitLib: A Formal Library for Language Generation in the Limit and AI-Assisted Mathematical Research](https://mlsanity.com/paper/2609.36663/) (2026)

## Abstract (arXiv)

We study language generation in the limit under a global preference ordering on strings, as introduced by Kleinberg and Wei. As is done in previous work, we aim for breadth, but impose an additional requirement of timeliness: higher-ranked strings should be generated earlier. A string is then only credited if it is generated before a deadline, where its deadline is defined by a function that maps a string's rank in the target language to the time by which it must be produced. This is in keeping with a central consideration in machine learning, where inductive bias favors ``simpler'' or ``more plausible'' outputs, all else being equal. We show that timely generation is impossible in a strong sense for eventually consistent generators -- the protagonists of most prior related work. Under what is perhaps the mildest natural relaxation of consistency, a hallucination rate that vanishes over time, we show that we can circumvent our impossibility result. In particular, we can achieve optimal density with respect to any superlinear deadline function. We also show this is tight by ruling out timely generation with linear deadlines and vanishing hallucination rate.