Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning

• URL: http://arxiv.org/abs/2505.11349v1
• Date: Fri, 16 May 2025 15:14:47 GMT
• Title: Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning
• Authors: Yuanzhao Zhang, William Gilpin,
• Abstract summary: We show that foundation models applied to physical systems can give accurate predictions, but that they fail to develop meaningful representations of the underlying physics.<n>Instead, foundation models often forecast by context parroting, a simple zero-shot forecasting strategy.<n>We draw a parallel between context parroting and induction heads, which explains why large language models trained on text can be repurposed for time series forecasting.
• Score: 6.445605125467573
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently-developed time series foundation models for scientific machine learning exhibit emergent abilities to predict physical systems. These abilities include zero-shot forecasting, in which a model forecasts future states of a system given only a short trajectory as context. Here, we show that foundation models applied to physical systems can give accurate predictions, but that they fail to develop meaningful representations of the underlying physics. Instead, foundation models often forecast by context parroting, a simple zero-shot forecasting strategy that copies directly from the context. As a result, a naive direct context parroting model scores higher than state-of-the-art time-series foundation models on predicting a diverse range of dynamical systems, at a tiny fraction of the computational cost. We draw a parallel between context parroting and induction heads, which explains why large language models trained on text can be repurposed for time series forecasting. Our dynamical systems perspective also ties the scaling between forecast accuracy and context length to the fractal dimension of the attractor, providing insight into the previously observed in-context neural scaling laws. Context parroting thus serves as a simple but tough-to-beat baseline for future time-series foundation models and can help identify in-context learning strategies beyond parroting.

Related papers

• Towards Interpretable Time Series Foundation Models [0.0]
  We generate natural language annotations using a large multimodal model and use these to supervise the fine-tuning of compact Qwen models.<n>Our results highlight the feasibility of compressing time series understanding into lightweight, language-capable models suitable for on-device or privacy-sensitive deployment.
  arXiv  Detail & Related papers  (2025-07-10T05:29:34Z)
• Deep learning framework for action prediction reveals multi-timescale locomotor control [41.985053522482545]
  We develop a deep learning-based framework for action prediction.<n>We find that neural network architectures with flexible input history- timescales, like GRU and Transformer, perform best overall.
  arXiv  Detail & Related papers  (2025-03-20T16:57:15Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• Context is Key: A Benchmark for Forecasting with Essential Textual Information [87.3175915185287]
  "Context is Key" (CiK) is a forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context.<n>We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters.<n>We propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark.
  arXiv  Detail & Related papers  (2024-10-24T17:56:08Z)
• Zero-shot forecasting of chaotic systems [6.445605125467573]
  Foundation models pre-trained on vast amounts of time-series data from diverse domains.<n>We evaluate whether the zero-shot learning paradigm extends to the challenging task of forecasting chaotic systems.
  arXiv  Detail & Related papers  (2024-09-24T05:56:58Z)
• Implicit Reasoning in Deep Time Series Forecasting [16.750280337155647]
  This work takes an initial step toward assessing the reasoning abilities of deep time series forecasting models. We find that certain linear, patch-based Transformer models generalize effectively in systematically orchestrated out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2024-09-17T02:11:19Z)
• The Power of Next-Frame Prediction for Learning Physical Laws [5.624870417352306]
  Next-frame prediction is a useful and powerful method for modelling and understanding the dynamics of video data. We introduce six diagnostic simulation video datasets derived from fundamental physical laws created by varying physical constants such as gravity and mass. We find that the generative training phase alone induces a model state that can predict physical constants significantly better than that of a random model.
  arXiv  Detail & Related papers  (2024-05-21T17:55:54Z)
• Interpretable Machine Learning for Weather and Climate Prediction: A Survey [24.028385794099435]
  We review current interpretable machine learning approaches applied to meteorological predictions. Design inherently interpretable models from scratch using architectures like tree ensembles and explainable neural networks. We discuss research challenges around achieving deeper mechanistic interpretations aligned with physical principles.
  arXiv  Detail & Related papers  (2024-03-24T14:23:35Z)
• Weather Prediction with Diffusion Guided by Realistic Forecast Processes [49.07556359513563]
  We introduce a novel method that applies diffusion models (DM) for weather forecasting. Our method can achieve both direct and iterative forecasting with the same modeling framework. The flexibility and controllability of our model empowers a more trustworthy DL system for the general weather community.
  arXiv  Detail & Related papers  (2024-02-06T21:28:42Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting [54.04430089029033]
  We present Lag-Llama, a general-purpose foundation model for time series forecasting based on a decoder-only transformer architecture. Lag-Llama is pretrained on a large corpus of diverse time series data from several domains, and demonstrates strong zero-shot generalization capabilities. When fine-tuned on relatively small fractions of such previously unseen datasets, Lag-Llama achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-10-12T12:29:32Z)
• Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale [54.15522908057831]
  We propose an adapted version of the computationally-Mixer for STTD forecast at scale. Our results surprisingly show that this simple-yeteffective solution can rival SOTA baselines when tested on several traffic benchmarks. Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
  arXiv  Detail & Related papers  (2023-07-04T05:19:19Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• Leveraging the structure of dynamical systems for data-driven modeling [111.45324708884813]
  We consider the impact of the training set and its structure on the quality of the long-term prediction. We show how an informed design of the training set, based on invariants of the system and the structure of the underlying attractor, significantly improves the resulting models.
  arXiv  Detail & Related papers  (2021-12-15T20:09:20Z)
• Generative Temporal Difference Learning for Infinite-Horizon Prediction [101.59882753763888]
  We introduce the $gamma$-model, a predictive model of environment dynamics with an infinite probabilistic horizon. We discuss how its training reflects an inescapable tradeoff between training-time and testing-time compounding errors.
  arXiv  Detail & Related papers  (2020-10-27T17:54:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.