Causal Graph based Event Reasoning using Semantic Relation Experts

2025-06-07

AI Summary

Existing large language models (LLMs) struggle to accurately identify causal relationships among events, limiting their performance on deep reasoning tasks such as event prediction and timeline understanding. To address this, we propose the “Semantic Relation Expert Collaborative Reasoning” framework: an LLM simulates multiple domain-specific experts—e.g., temporal, logical, and enabling-relations experts—who engage in iterative deliberation to explicitly construct fine-grained causal event graphs (e.g., “A enables B”). We innovatively formalize an interpretable event prediction task requiring models to output complete causal chains, thereby significantly enhancing reasoning transparency and logical coherence. Our approach requires no model fine-tuning and operates purely in a zero-shot setting. It achieves state-of-the-art performance on both general event prediction and next-event prediction benchmarks. Moreover, the generated causal explanations are more accurate, information-rich, and structurally rigorous than prior methods.

Technology Category

• Reasoning under Uncertainty: Causality
• Knowledge Representation and Reasoning: Action, Change, and Causality
• 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
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Understanding how events in a scenario causally connect with each other is important for effectively modeling and reasoning about events. But event reasoning remains a difficult challenge, and despite recent advances, Large Language Models (LLMs) still struggle to accurately identify causal connections between events. This struggle leads to poor performance on deeper reasoning tasks like event forecasting and timeline understanding. To address this challenge, we investigate the generation of causal event graphs (e.g., A enables B) as a parallel mechanism to help LLMs explicitly represent causality during inference. This paper evaluates both how to generate correct graphs as well as how graphs can assist reasoning. We propose a collaborative approach to causal graph generation where we use LLMs to simulate experts that focus on specific semantic relations. The experts engage in multiple rounds of discussions which are then consolidated by a final expert. Then, to demonstrate the utility of causal graphs, we use them on multiple downstream applications, and also introduce a new explainable event prediction task that requires a causal chain of events in the explanation. These explanations are more informative and coherent than baseline generations. Finally, our overall approach not finetuned on any downstream task, achieves competitive results with state-of-the-art models on both forecasting and next event prediction tasks.

Problem

• Improving causal connection identification between events
• Generating accurate causal event graphs for reasoning
• Enhancing event forecasting and timeline understanding tasks

Innovation

• Generates causal event graphs for LLMs
• Uses LLM-simulated semantic relation experts
• Applies graphs to explainable event prediction