Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic
This work addresses a specific limitation in LLMs for temporal reasoning, offering a domain-specific solution that is incremental in nature.
The paper tackles the challenge of temporal reasoning in large language models (LLMs) by proposing TempLogic, a framework that improves performance on complex temporal question-answering tasks through retrieval-guided context distillation, temporal data extraction, and custom logic reasoning.
The temporal aspect is a significant dimension of our reality. We notice the challenge that large language models (LLMs) face when engaging in temporal reasoning. Our preliminary experiments show that methods involving the generation of intermediate reasoning steps, such as chain-of-thought and program-aided language models, do not consistently boost the performance of complex temporal question-answering tasks. This limitation can be attributed to the LLMs' inadequate understanding of temporal information. To address this problem, we propose TempLogic, a novel framework designed specifically for temporal question-answering tasks across three levels of reasoning. TempLogic incorporates retrieval-guided context distillation, temporal data extraction, and tailor-made logic reasoning. Extensive experiments and analysis demonstrate the effectiveness of our framework in solving intricate time-bound reasoning tasks.