AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models

TL;DR

AdapTime is a novel adaptive reasoning method that dynamically guides large language models through temporal questions, improving their temporal reasoning without external tools.

Contribution

It introduces a flexible, input-dependent reasoning framework with an LLM planner, enhancing temporal reasoning in LLMs over fixed pipelines.

Findings

Significantly improves temporal reasoning accuracy.

Reduces unnecessary processing for simple questions.

Enhances reasoning for complex temporal queries.

Abstract

Large language models have demonstrated strong reasoning capabilities in general knowledge question answering. However, their ability to handle temporal information remains limited. To address this limitation, existing approaches often involve external tools or manual verification and are tailored to specific scenarios, leading to poor generalizability. Moreover, these methods apply a fixed pipeline to all questions, overlooking the fact that different types of temporal questions require distinct reasoning strategies, which leads to unnecessary processing for simple cases and inadequate reasoning for complex ones. To this end, we propose AdapTime, an adaptive temporal reasoning method that dynamically executes reasoning steps based on the input context. Specifically, it involves three temporal reasoning actions: reformulate, rewrite and review, with an LLM planner guiding the reasoning process. AdapTime integrates seamlessly with state-of-the-art LLMs and significantly enhances their temporal reasoning capabilities without relying on external support. Extensive experiments demonstrate the effectiveness of our approach.