Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.03701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913090759557120 |
|---|---|
| author | Hao, Zhifeng Chen, Zhongjie Lu, Junhao Yu, Shengyin Hu, Guimin Zhang, Keli Cai, Ruichu Xu, Boyan |
| author_facet | Hao, Zhifeng Chen, Zhongjie Lu, Junhao Yu, Shengyin Hu, Guimin Zhang, Keli Cai, Ruichu Xu, Boyan |
| contents | Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks, their effectiveness in ECI remains limited due to biases in causal reasoning, often leading to overprediction of causal relationships (causal hallucination). To mitigate these issues and enhance LLM performance in ECI, we propose SERE, a structural example retrieval framework that leverages LLMs' few-shot learning capabilities. SERE introduces an innovative retrieval mechanism based on three structural concepts: (i) Conceptual Path Metric, which measures the conceptual relationship between events using edit distance in ConceptNet; (ii) Syntactic Metric, which quantifies structural similarity through tree edit distance on syntactic trees; and (iii) Causal Pattern Filtering, which filters examples based on predefined causal structures using LLMs. By integrating these structural retrieval strategies, SERE selects more relevant examples to guide LLMs in causal reasoning, mitigating bias and improving accuracy in ECI tasks. Extensive experiments on multiple ECI datasets validate the effectiveness of SERE. The source code is publicly available at https://github.com/DMIRLAB-Group/SERE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03701 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification Hao, Zhifeng Chen, Zhongjie Lu, Junhao Yu, Shengyin Hu, Guimin Zhang, Keli Cai, Ruichu Xu, Boyan Computation and Language Artificial Intelligence Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Large Language Models (LLMs) have demonstrated strong performance across various NLP tasks, their effectiveness in ECI remains limited due to biases in causal reasoning, often leading to overprediction of causal relationships (causal hallucination). To mitigate these issues and enhance LLM performance in ECI, we propose SERE, a structural example retrieval framework that leverages LLMs' few-shot learning capabilities. SERE introduces an innovative retrieval mechanism based on three structural concepts: (i) Conceptual Path Metric, which measures the conceptual relationship between events using edit distance in ConceptNet; (ii) Syntactic Metric, which quantifies structural similarity through tree edit distance on syntactic trees; and (iii) Causal Pattern Filtering, which filters examples based on predefined causal structures using LLMs. By integrating these structural retrieval strategies, SERE selects more relevant examples to guide LLMs in causal reasoning, mitigating bias and improving accuracy in ECI tasks. Extensive experiments on multiple ECI datasets validate the effectiveness of SERE. The source code is publicly available at https://github.com/DMIRLAB-Group/SERE. |
| title | SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.03701 |