Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle

Many existing evaluation benchmarks for Large Language Models (LLMs) quickly become outdated due to the emergence of new models and training data. These benchmarks also fall short in assessing how LLM performance changes over time, as they consist of static questions without a temporal dimension. To...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-11
Main Authors: Dai, Hui, Teehan, Ryan, Ren, Mengye
Format: Article
Language:English
Subjects:
Benchmarks
Large language models
Performance degradation
Performance evaluation
Questions
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many existing evaluation benchmarks for Large Language Models (LLMs) quickly become outdated due to the emergence of new models and training data. These benchmarks also fall short in assessing how LLM performance changes over time, as they consist of static questions without a temporal dimension. To address these limitations, we propose using future event prediction as a continuous evaluation method to assess LLMs' temporal generalization and forecasting abilities. Our benchmark, Daily Oracle, automatically generates question-answer (QA) pairs from daily news, challenging LLMs to predict "future" event outcomes. Our findings reveal that as pre-training data becomes outdated, LLM performance degrades over time. While Retrieval Augmented Generation (RAG) has the potential to enhance prediction accuracy, the performance degradation pattern persists, highlighting the need for continuous model updates.
ISSN:2331-8422