# Thoth: Mid-Training Bridges LLMs to Time Series Understanding

arXiv: https://arxiv.org/abs/2603.01042 · HTML: https://mlsanity.com/paper/2603.01042/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Llemma: An Open Language Model For Mathematics](https://mlsanity.com/paper/2310.10631/) (2023)
- [ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning](https://mlsanity.com/paper/2412.03104/) (2024)
- [ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data](https://mlsanity.com/paper/2412.11376/) (2024)
- [Language Models Still Struggle to Zero-shot Reason about Time Series](https://mlsanity.com/paper/2404.11757/) (2024)
- [Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement](https://mlsanity.com/paper/2503.01875/) (2025)
- [MTBench: A Multimodal Time Series Benchmark for Temporal Reasoning and Question Answering](https://mlsanity.com/paper/2503.16858/) (2025)
- [ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset](https://mlsanity.com/paper/2506.20093/) (2025)
- [GeoGalactica: A Scientific Large Language Model in Geoscience](https://mlsanity.com/paper/2401.00434/) (2023)
- [TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models](https://mlsanity.com/paper/2509.24803/) (2025)
- [A Survey on LLM Mid-Training](https://mlsanity.com/paper/2510.23081/) (2025)
- [Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language](https://mlsanity.com/paper/2512.11251/) (2025)

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

- [FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models](https://mlsanity.com/paper/2605.03460/) (2026)
- [ReasonCast: Towards Explainable Time Series Forecasting with Reasoning](https://mlsanity.com/paper/2608.01875/) (2026)
- [CodeTS: Verifiable Text-to-Time Series Generation via Executable Code](https://mlsanity.com/paper/2609.15393/) (2026)
- [GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation](https://mlsanity.com/paper/2610.17794/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable success in general-purpose reasoning. However, they still struggle to understand and reason about time series data, which limits their effectiveness in decision-making scenarios that depend on temporal dynamics. In this paper, we propose Thoth, the first family of mid-trained LLMs with general-purpose time series understanding capabilities. As a pivotal intermediate stage, mid-training achieves task- and domain-agnostic alignment between time series and natural language, for which we construct Book-of-Thoth, a high-quality, time-series-centric mid-training corpus. Book-of-Thoth enables both time-series-to-text and text-to-time-series generation, equipping LLMs with a foundational grasp of temporal patterns. To better evaluate advanced reasoning capabilities, we further present KnoTS, a novel benchmark of knowledge-intensive time series understanding, designed for joint reasoning over temporal patterns and domain knowledge. Extensive experiments demonstrate that mid-training with Book-of-Thoth enables Thoth to significantly outperform its base model and advanced LLMs across a range of time series question answering benchmarks. Moreover, Thoth exhibits superior capabilities when fine-tuned under data scarcity, underscoring the effectiveness of mid-training for time series understanding. Code is available at: https://github.com/thuml/Thoth.