Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models

ACL ARR 2025 February Submission5942 Authors

Abstract: 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 event relations. 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.

Paper Type: Short

Research Area: Information Extraction

Research Area Keywords: Event extraction,Reasoning,Prompting

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 5942