Pith. sign in

REVIEW 6 cited by

Language Models Still Struggle to Zero-shot Reason about Time Series

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.11757 v1 pith:DAJLSYUW submitted 2024-04-17 cs.CL

classification cs.CL
keywords seriestimelanguagemodelsreasoningforecastingmodelanswering
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Time series are critical for decision-making in fields like finance and healthcare. Their importance has driven a recent influx of works passing time series into language models, leading to non-trivial forecasting on some datasets. But it remains unknown whether non-trivial forecasting implies that language models can reason about time series. To address this gap, we generate a first-of-its-kind evaluation framework for time series reasoning, including formal tasks and a corresponding dataset of multi-scale time series paired with text captions across ten domains. Using these data, we probe whether language models achieve three forms of reasoning: (1) Etiological Reasoning - given an input time series, can the language model identify the scenario that most likely created it? (2) Question Answering - can a language model answer factual questions about time series? (3) Context-Aided Forecasting - does highly relevant textual context improve a language model's time series forecasts? We find that otherwise highly-capable language models demonstrate surprisingly limited time series reasoning: they score marginally above random on etiological and question answering tasks (up to 30 percentage points worse than humans) and show modest success in using context to improve forecasting. These weakness showcase that time series reasoning is an impactful, yet deeply underdeveloped direction for language model research. We also make our datasets and code public at to support further research in this direction at https://github.com/behavioral-data/TSandLanguage

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Overcoming the Modality Gap in Context-Aided Forecasting

    cs.LG 2026-03 unverdicted novelty 7.0 of 10

    A semi-synthetic dataset of 7 million context-augmented time series windows with verifier-filtered contexts enables transfer to real-world context-aided forecasting and suggests data quality—not architecture—was the b...

  2. TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning

    cs.LG 2026-07 conditional novelty 6.5 of 10

    A heterogeneous-graph router jointly selects the optimal modality (text, vision, or both) and model per time series query, beating prior routing baselines and generalizing to unseen models and tasks.

  3. Using LLMs for Explainable, Data-Driven Insight Generation from Time Series

    cs.AI 2026-06 conditional novelty 6.0 of 10

    A modular LLM pipeline extracts explanatory factors from analyst text, conditions evidence-based report generation, and evaluates readability, consistency, and persuasiveness, reportedly matching analyst reports on re...

  4. TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Reinforcement learning with a composite reward lifts Qwen2.5-VL-3B to 75.29% average accuracy on TIMERBED, above prompt-based GPT-4o and classical time-series baselines.

  5. Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decision

    cs.AI 2025-06 reject novelty 6.0 of 10

    A three-turn prompting framework, ReasonTSC, boosts LLM time series classification by fusing pattern analysis with plug-in model scores, but its evaluation leaks test-set labels into the prompts and overstates the gains.

  6. Unified Multimodal Understanding via Byte-Pair Visual Encoding

    cs.CV 2025-06 conditional novelty 4.0 of 10

    Priority-guided byte-pair encoding of quantized image patches plus curriculum training yields an 8B discrete-token MLLM competitive with continuous-embedding models on VQA and multimodal benchmarks.

Pith tools