# What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?

arXiv: https://arxiv.org/abs/2603.19017 · HTML: https://mlsanity.com/paper/2603.19017/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 16 of its 18 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 16 of 16)

- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models](https://mlsanity.com/paper/2305.13707/) (2023)
- [FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language](https://mlsanity.com/paper/2506.20920/) (2025)
- [Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs](https://mlsanity.com/paper/2402.14903/) (2024)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [ChronoSense: Exploring Temporal Understanding in Large Language Models with Time Intervals of Events](https://mlsanity.com/paper/2501.03040/) (2025)
- [The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspaces](https://mlsanity.com/paper/2410.13194/) (2024)
- [Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs](https://mlsanity.com/paper/2502.05092/) (2025)
- [Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks](https://mlsanity.com/paper/2509.20045/) (2025)
- [Around the World in 24 Hours: Probing LLM Knowledge of Time and Place](https://mlsanity.com/paper/2506.03984/) (2025)
- [Efficient numeracy in language models through single-token number embeddings](https://mlsanity.com/paper/2510.06824/) (2025)
- [Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning](https://mlsanity.com/paper/2505.16088/) (2025)
- [Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time](https://mlsanity.com/paper/2508.02037/) (2025)
- [LLMLagBench: Identifying Temporal Training Boundaries in Large Language Models](https://mlsanity.com/paper/2511.12116/) (2025)
- [Can Language Models Handle a Non-Gregorian Calendar? The Case of the Japanese wareki](https://mlsanity.com/paper/2509.04432/) (2025)
- [Measuring Iterative Temporal Reasoning with Time Puzzles](https://mlsanity.com/paper/2601.07148/) (2026)

## Built on by (most cited first, 1 of 1)

- [Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning Models](https://mlsanity.com/paper/2606.12689/) (2026)

## Abstract (arXiv)

We present MultiTempBench, a multilingual temporal reasoning benchmark spanning three tasks, date arithmetic, time zone conversion, and temporal relation extraction across five languages (English, German, Chinese, Arabic, and Hausa) and multiple calendar conventions (Gregorian, Hijri, and Chinese Lunar). MultiTempBench contains 15,000 examples built by translating 750 curated English questions and expanding each into controlled date-format variants. We evaluate 20 LLMs and introduce the multilingual Date Fragmentation Ratio (mDFR), calibrated with human severity ratings, together with geometric-probing analyses of internal temporal representations. We find tokenisation quality of temporal artefacts is a resource-dependent bottleneck: in low-resource languages and rarer calendar formats, fragmentation disrupts Year/Month/Day separation and accuracy collapses, while high-resource settings are often robust to digit-level splitting. Beyond tokenisation, crossed mixed-effects regression shows that temporal linearity is the strongest predictor of temporal reasoning in high-resource languages, whereas fragmentation is the stronger predictor in low-resource languages. Code is available at: https://github.com/gagan3012/mtb