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

2025-06-06

AI Summary

Existing zero-shot event causal identification (ECI) methods rely on labeled data, while large language models (LLMs), though capable of zero-shot inference, frequently generate causal hallucinations. To address this, we propose a multi-source evidence decomposition and fuzzy aggregation framework. Our method structurally decomposes causal reasoning into interpretable subtasks—including temporal ordering, necessity, and sufficiency—and employs multi-task prompting to elicit fine-grained, uncertainty-aware LLM responses. We explicitly model output uncertainty and design a fuzzy logic-based aggregation mechanism to integrate evidence from multiple subtasks, thereby suppressing spurious causal inferences. Evaluated on three standard benchmarks, our approach achieves improvements of 6.2% in F1-score and 9.3% in precision, with a significant reduction in causal hallucination errors. This work is the first to introduce structured causal decomposition coupled with uncertainty-aware aggregation into zero-shot ECI, establishing a novel paradigm for robust causal judgment.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

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.

Problem

• Detect causal relationships between events in text
• Reduce dependence on large-scale annotated data
• Mitigate causal hallucination errors in LLMs

Innovation

• Multi-source Evidence Fuzzy Aggregation framework
• Decomposes causality into three main tasks
• Uses LLMs for zero-shot causality scoring