Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering
This addresses the challenge of accurate time-sensitive question answering for users needing reliable temporal reasoning, representing an incremental advancement in bridging the human-machine gap.
The paper tackles the problem of limited temporal sensitivity and reasoning in large language models for Time-Sensitive Question Answering (TSQA) by proposing a novel framework, achieving significant performance improvements over existing LLMs on four TSQA datasets.
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.