Pith. sign in

REVIEW 4 cited by

Are Language Models Actually Useful for Time Series Forecasting?

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2406.16964 v2 pith:BZYEN23M submitted 2024-06-22 cs.LG cs.AI

Mingtian Tan , Mike A. Merrill , Vinayak Gupta , Tim Althoff , Thomas Hartvigsen This is my paper · ORCID
classification cs.LGcs.AI
keywords seriestimeforecastingmodelsfindlanguageactuallyattention
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) are being applied to time series forecasting. But are language models actually useful for time series? In a series of ablation studies on three recent and popular LLM-based time series forecasting methods, we find that removing the LLM component or replacing it with a basic attention layer does not degrade forecasting performance -- in most cases, the results even improve! We also find that despite their significant computational cost, pretrained LLMs do no better than models trained from scratch, do not represent the sequential dependencies in time series, and do not assist in few-shot settings. Additionally, we explore time series encoders and find that patching and attention structures perform similarly to LLM-based forecasters.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. CSI-4CAST: A Hybrid Deep Learning Model for CSI Prediction with Comprehensive Robustness and Generalization Testing

    cs.LG 2025-10 conditional novelty 5.0 of 10

    A hybrid CNN-ShuffleNet-Transformer model claims the best accuracy-efficiency trade-off on a new 3,060-scenario CSI prediction benchmark, but FDD gains and robustness claims rest on point estimates without error bars.

  2. Integrating Traditional Technical Analysis with AI: A Multi-Agent LLM-Based Approach to Stock Market Forecasting

    cs.CE 2025-06 reject novelty 5.0 of 10

    An LLM-based multi-agent system that identifies Elliott Wave patterns achieved 44-89% directional accuracy on six US stocks, with deep reinforcement learning backtesting improving accuracy on most but not all test cases.

  3. TempoGPT: Enhancing Time Series Reasoning via Quantizing Embedding

    cs.LG 2025-01 conditional novelty 5.0 of 10

    Converting time series into discrete tokens via a VQ-VAE codebook and feeding them through a shared embedding layer with text improves a language model's accuracy on a synthetic circuit-based time series reasoning benchmark.

  4. ElliottAgents: A Natural Language-Driven Multi-Agent System for Stock Market Analysis and Prediction

    cs.CE 2025-07 reject novelty 3.0 of 10

    A natural-language multi-agent system combines Elliott Wave pattern detection with LLM dialogue and DRL backtesting to generate stock predictions, supported only by small selected experiments.

Pith tools