paper-with-me

홈 › Papers

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

2025-02-17 · Jongho Kim, Seung-won Hwang

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.

📄 PDF Abstract BibTeX arXiv:2502.11425

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactual

Similar Papers 제목 키워드 기반

Understanding Physical Dynamics with Counterfactual World Modeling

2023-12-11 · Rahul Venkatesh, Honglin Chen, Kevin Feigelis, Daniel M. Bear 외

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…

counterfactual

Reasoning Beyond Bias: A Study on Counterfactual Prompting and Chain of Thought Reasoning

2024-08-16 · Kyle Moore, Jesse Roberts, Thao Pham, Douglas Fisher

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 Understanding

Prompting Large Language Models for Counterfactual Generation: An Empirical Study

2023-05-24 · Yongqi Li, Mayi Xu, Xin Miao, Shen Zhou 외

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+5

LLMs Are Prone to Fallacies in Causal Inference

2024-06-18 · Nitish Joshi, Abulhair Saparov, Yixin Wang, He He

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

2021-06-16 · Hung Le, Nancy F. Chen, Steven C. H. Hoi

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