ChatTS: Aligning Time Series With LLMs Via Synthetic Data For Enhanced Understanding And Reasoning
Source
- Raw Markdown: paper_chatts-2024.md
- PDF: paper_chatts-2024.pdf
Core Claim
ChatTS treats time series as a modality for multimodal LLMs and uses synthetic time-series/text data to train understanding and reasoning over multivariate series.
Key Contributions
- Proposes attribute-based synthetic time-series generation with detailed textual descriptions.
- Introduces Time Series Evol-Instruct for diverse time-series Q&A data.
- Builds a context-aware time-series encoder for variable-length multivariate inputs.
- Reports strong gains over vision-based, text-based, and agent-based baselines on alignment and reasoning tasks.
Method Notes
ChatTS is linked to Time-Series Foundation Models and Synthetic Data For Time Series. It is also a precursor to the reasoning-oriented TimeOmni-1 and generation-oriented TimeOmni-VL.
Evidence And Results
The abstract reports a 46.0% improvement in alignment tasks and a 25.8% improvement in reasoning tasks over listed baselines, using real-world benchmark evaluation after synthetic training.
Limitations
The approach depends heavily on synthetic attribute coverage and evaluation design. The paper does not by itself prove general-purpose time-series reasoning beyond its task suite.
Foundation TSFM Relevance
| Agenda slot | Verdict | Evidence | Missing pieces |
|---|---|---|---|
| Context interface | partially closes | Token-level concatenation preserves the position of multivariate series inside the surrounding text query and context. | Context is mostly textual/query context, not system topology, events, or actions. |
| Representation quality: semantic state vs dense numeric detail | partially closes | Value-preserved normalization adds scaling and offset information so the LLM can answer numerical queries after normalization. | Does not prove dense reconstruction, editing, or calibrated future generation. |
| Benchmarks: what level of modeling is tested? | partially closes | Evaluates alignment and reasoning tasks including trend, seasonality, local fluctuation, correlation, clustering, inductive, deductive, and causal QA. | Evaluation is synthetic-heavy and excludes domain-specific classification and etiological reasoning. |
Links Into The Wiki
- ChatTS
- Time-Series Foundation Models
- Foundation Time-Series Model Research Agenda
- Synthetic Data For Time Series
Open Questions
- Which attributes are sufficient for robust time-series-language grounding?
- How does ChatTS compare against reasoning-specific RL/post-training approaches?