Context is Key: A Benchmark for Forecasting with Essential Textual Information

Andrew Robert Williams, Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Jithendaraa Subramanian +6 more
2/14/2026

No official code found. Best implementation: ServiceNow/context-is-key-forecasting (100 stars, Apache-2.0, last commit 2026-02-11).

Semantic Scholar

Code Implementations(1)

ServiceNow/context-is-key-forecastingCommunity63%
Apache-2.0

Context is Key: A Benchmark for Forecasting with Essential Textual Information

10014Shell, PythonOct 7, 20248 months agoApache-2.0

Similar Papers

CPPO: Continual Learning for Reinforcement Learning with Human Feedback

94% match2026

Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training

94% match2026

Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation

93% match2026

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement

93% match1 repo602026

Active Negative Loss Functions for Learning with Noisy Labels

93% match2026

FIG: Flow with Interpolant Guidance for Linear Inverse Problems

92% match1 repo2026

Cite this paper

@article{williams2026context,
  title  = {Context is Key: A Benchmark for Forecasting with Essential Textual Information},
  author = {Andrew Robert Williams and Arjun Ashok and Étienne Marcotte and Valentina Zantedeschi and Jithendaraa Subramanian and Roland Riachi and James Requeima and Alexandre Lacoste and Irina Rish and Nicolas Chapados and Alexandre Drouin},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:4a2b1b4c0de1ed2a2b25a40c57e8bd4b595cf2bd},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/4a2b1b4c0de1ed2a2b25a40c57e8bd4b595cf2bd.svg)](https://codeofpaper.com/paper/4a2b1b4c0de1ed2a2b25a40c57e8bd4b595cf2bd)

Discussion