Papers with causality existence identification
Evaluating Instructively Generated Statement by Large Language Models for Directional Event Causality Identification (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on identifying existence of causality between two event mentions, but the direction of causalities is crucial for understanding the causal relation. |
| Approach: | They propose to instruct a GLM to generate causality statements and identify directional event causality by evaluating the generated statements. |
| Outcome: | The proposed method significantly outperforms state-of-the-art methods even with fewer training data. |
Identifying while Learning for Document Event Causality Identification (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on causality existence, but ignore causal direction. |
| Approach: | They propose a new *identifying while learning* mode for the ECI task that takes care of the causal direction and updates events’ representations for boosting next round of causality identification. |
| Outcome: | The proposed method outperforms the state-of-the-art methods on two public datasets. |