AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Deng, Yimin, Wang, Yejing, Lin, Zhenxi, Fu, Zichuan, Zhao, Guoshuai, Xu, Derong, Zheng, Yefeng, Zhao, Xiangyu, Wu, Xian, Zhu, Li, Qian, Xueming
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915960746672128
author Deng, Yimin
Wang, Yejing
Lin, Zhenxi
Fu, Zichuan
Zhao, Guoshuai
Xu, Derong
Zheng, Yefeng
Zhao, Xiangyu
Wu, Xian
Zhu, Li
Qian, Xueming
author_facet Deng, Yimin
Wang, Yejing
Lin, Zhenxi
Fu, Zichuan
Zhao, Guoshuai
Xu, Derong
Zheng, Yefeng
Zhao, Xiangyu
Wu, Xian
Zhu, Li
Qian, Xueming
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_24175
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models
Deng, Yimin
Wang, Yejing
Lin, Zhenxi
Fu, Zichuan
Zhao, Guoshuai
Xu, Derong
Zheng, Yefeng
Zhao, Xiangyu
Wu, Xian
Zhu, Li
Qian, Xueming
Computation and Language
Artificial Intelligence
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.
title AdapTime: Enabling Adaptive Temporal Reasoning in Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.24175