Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualSimilar Papers 제목 키워드 기반
Understanding Physical Dynamics with Counterfactual World Modeling
The ability to understand physical dynamics is critical for agents to act in the world. Here, we use Counterfactual World Modeling (CWM) to extract vision structures for dynamics understanding. CWM uses a temporally-fact…
counterfactualReasoning Beyond Bias: A Study on Counterfactual Prompting and Chain of Thought Reasoning
Language models are known to absorb biases from their training data, leading to predictions driven by statistical regularities rather than semantic relevance. We investigate the impact of these biases on answer choice pr…
counterfactualMMLUMulti-task Language UnderstandingPrompting Large Language Models for Counterfactual Generation: An Empirical Study
Large language models (LLMs) have made remarkable progress in a wide range of natural language understanding and generation tasks. However, their ability to generate counterfactuals has not been examined systematically. …
counterfactualData Augmentationnamed-entity-recognitionNamed Entity Recognition+5LLMs Are Prone to Fallacies in Causal Inference
Recent work shows that causal facts can be effectively extracted from LLMs through prompting, facilitating the creation of causal graphs for causal inference tasks. However, it is unclear if this success is limited to ex…
Causal Inferencecounterfactual$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues
Video-grounded dialogue systems aim to integrate video understanding and dialogue understanding to generate responses that are relevant to both the dialogue and video context. Most existing approaches employ deep learnin…
Contrastive LearningcounterfactualDialogue UnderstandingMultimodal Reasoning+1