TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
This addresses the problem of evaluating temporal reasoning abilities in large language models for AI researchers, though it is incremental as it builds on existing benchmarks by providing a more comprehensive framework.
The authors tackled the lack of a comprehensive temporal reasoning benchmark by proposing TimeBench, a hierarchical evaluation covering various temporal reasoning phenomena, and found a significant performance gap between state-of-the-art large language models and humans, with LLMs showing discrepancies across reasoning categories.
Grasping the concept of time is a fundamental facet of human cognition, indispensable for truly comprehending the intricacies of the world. Previous studies typically focus on specific aspects of time, lacking a comprehensive temporal reasoning benchmark. To address this, we propose TimeBench, a comprehensive hierarchical temporal reasoning benchmark that covers a broad spectrum of temporal reasoning phenomena. TimeBench provides a thorough evaluation for investigating the temporal reasoning capabilities of large language models. We conduct extensive experiments on GPT-4, LLaMA2, and other popular LLMs under various settings. Our experimental results indicate a significant performance gap between the state-of-the-art LLMs and humans, highlighting that there is still a considerable distance to cover in temporal reasoning. Besides, LLMs exhibit capability discrepancies across different reasoning categories. Furthermore, we thoroughly analyze the impact of multiple aspects on temporal reasoning and emphasize the associated challenges. We aspire for TimeBench to serve as a comprehensive benchmark, fostering research in temporal reasoning. Resources are available at: https://github.com/zchuz/TimeBench