# Zero-Shot Event Causality Identification via Multi-source Evidence Fuzzy Aggregation with Large Language Models

arXiv: https://arxiv.org/abs/2506.05675 · HTML: https://mlsanity.com/paper/2506.05675/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 59 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation](https://mlsanity.com/paper/2305.07375/) (2023)
- [MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction](https://mlsanity.com/paper/2211.07342/) (2022)
- [DeepRAG: Thinking to Retrieve Step by Step for Large Language Models](https://mlsanity.com/paper/2502.01142/) (2025)
- [Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement](https://mlsanity.com/paper/2106.01654/) (2021)
- [ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification](https://mlsanity.com/paper/2204.07434/) (2022)
- [Extracting Temporal and Causal Relations between Events](https://mlsanity.com/paper/1604.08120/) (2016)
- [LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification](https://mlsanity.com/paper/2106.01649/) (2021)
- [Uncertainty-aware Language Modeling for Selective Question Answering](https://mlsanity.com/paper/2311.15451/) (2023)
- [Semantic Structure Enhanced Event Causality Identification](https://mlsanity.com/paper/2305.12792/) (2023)
- [CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision](https://mlsanity.com/paper/2107.09852/) (2021)
- [Document-level Causal Relation Extraction with Knowledge-guided Binary Question Answering](https://mlsanity.com/paper/2410.04752/) (2024)
- [Causality extraction from medical text using Large Language Models (LLMs)](https://mlsanity.com/paper/2407.10020/) (2024)
- [Identifying while Learning for Document Event Causality Identification](https://mlsanity.com/paper/2405.20608/) (2024)
- [A Survey of Event Causality Identification: Taxonomy, Challenges, Assessment, and Prospects](https://mlsanity.com/paper/2411.10371/) (2024)
- [DAPrompt: Deterministic Assumption Prompt Learning for Event Causality Identification](https://mlsanity.com/paper/2307.09813/) (2023)
- [Generalizing the Dempster-Shafer Theory to Fuzzy Sets](https://mlsanity.com/paper/1304.2383/) (2013)
- [Advancing Event Causality Identification via Heuristic Semantic Dependency Inquiry Network](https://mlsanity.com/paper/2409.13621/) (2024)

## Abstract (arXiv)

Event Causality Identification (ECI) aims to detect causal relationships between events in textual contexts. Existing ECI models predominantly rely on supervised methodologies, suffering from dependence on large-scale annotated data. Although Large Language Models (LLMs) enable zero-shot ECI, they are prone to causal hallucination-erroneously establishing spurious causal links. To address these challenges, we propose MEFA, a novel zero-shot framework based on Multi-source Evidence Fuzzy Aggregation. First, we decompose causality reasoning into three main tasks (temporality determination, necessity analysis, and sufficiency verification) complemented by three auxiliary tasks. Second, leveraging meticulously designed prompts, we guide LLMs to generate uncertain responses and deterministic outputs. Finally, we quantify LLM's responses of sub-tasks and employ fuzzy aggregation to integrate these evidence for causality scoring and causality determination. Extensive experiments on three benchmarks demonstrate that MEFA outperforms second-best unsupervised baselines by 6.2% in F1-score and 9.3% in precision, while significantly reducing hallucination-induced errors. In-depth analysis verify the effectiveness of task decomposition and the superiority of fuzzy aggregation.