Time machine GPT

Conference item

Large language models (LLMs) are often trained on extensive, temporally indiscriminate text corpora, reflecting the lack of datasets with temporal metadata. This approach is not aligned with the evolving nature of language. Conventional methods for creating temporally adapted language models often depend on further pre-training static models on time-specific data. This paper presents a new approach: a series of point-in-time LLMs called Time Machine GPT (TiMaGPT), specifically designed to be nonprognosticative. This ensures they remain uninformed about future factual information and linguistic changes. This strategy is beneficial for understanding language evolution and is of critical importance when applying models in dynamic contexts, such as time-series forecasting, where foresight of future information can prove problematic. We provide access to both the models and training datasets.

Authors: Drinkall, F; Rahimikia, E; Pierrehumbert, J; Zohren, S

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Association for Computational Linguistics
• Host title: Findings of the Association for Computational Linguistics: NAACL 2024
• Pages: 3281–3292
• Publication date: 2024-06-16
• Acceptance date: 2024-04-03
• Event title: 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics
• Event location: Mexico City, Mexico
• Event website: https://2024.naacl.org/
• Event start date: 2024-06-16
• Event end date: 2024-06-21
• DOI: 10.18653/v1/2024.findings-naacl.208
• ISBN: 9798891761193
• Language: English