Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering

TL;DR

This paper introduces a new framework that improves large language models' ability to understand and reason about time-sensitive questions by enhancing temporal awareness through specialized embeddings and reinforcement learning, leading to better performance on TSQA datasets.

Contribution

The paper presents a novel framework combining Temporal Information-Aware Embedding and Granular Contrastive Reinforcement Learning to boost temporal reasoning in LLMs for TSQA.

Findings

Significant performance improvements on four TSQA datasets.

Enhanced temporal sensitivity and reasoning capabilities in LLMs.

Bridging the gap between machine and human temporal understanding.

Abstract

Time-Sensitive Question Answering (TSQA) demands the effective utilization of specific temporal contexts, encompassing multiple time-evolving facts, to address time-sensitive questions. This necessitates not only the parsing of temporal information within questions but also the identification and understanding of time-evolving facts to generate accurate answers. However, current large language models still have limited sensitivity to temporal information and their inadequate temporal reasoning capabilities. In this paper, we propose a novel framework that enhances temporal awareness and reasoning through Temporal Information-Aware Embedding and Granular Contrastive Reinforcement Learning. Experimental results on four TSQA datasets demonstrate that our framework significantly outperforms existing LLMs in TSQA tasks, marking a step forward in bridging the performance gap between machine and human temporal understanding and reasoning.