Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models
This addresses a key limitation in LLMs for applications requiring precise temporal reasoning, though it appears incremental relative to prior work on temporal consistency.
The paper tackles temporal inconsistency in large language models by proposing a novel counterfactual prompting approach, demonstrating significant improvements in event ordering and temporal commonsense understanding across multiple datasets.
Despite the advanced capabilities of large language models (LLMs), their temporal reasoning ability remains underdeveloped. Prior works have highlighted this limitation, particularly in maintaining temporal consistency when understanding events. For example, models often confuse mutually exclusive temporal relations like ``before'' and ``after'' between events and make inconsistent predictions. In this work, we tackle the issue of temporal inconsistency in LLMs by proposing a novel counterfactual prompting approach. Our method generates counterfactual questions and enforces collective constraints, enhancing the model's consistency. We evaluate our method on multiple datasets, demonstrating significant improvements in event ordering for explicit and implicit events and temporal commonsense understanding by effectively addressing temporal inconsistencies.