# Beyond LLMs: A Linguistic Approach to Causal Graph Generation from Narrative Texts

arXiv: https://arxiv.org/abs/2504.07459 · HTML: https://mlsanity.com/paper/2504.07459/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 71 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Builds on (most cited first, 14 of 14)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Neural Text Summarization: A Critical Evaluation](https://mlsanity.com/paper/1908.08960/) (2019)
- [Guided Generation of Cause and Effect](https://mlsanity.com/paper/2107.09846/) (2021)
- [CausalKG: Causal Knowledge Graph Explainability using interventional and counterfactual reasoning](https://mlsanity.com/paper/2201.03647/) (2022)
- [Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset](https://mlsanity.com/paper/2211.00869/) (2022)
- [UniCausal: Unified Benchmark and Repository for Causal Text Mining](https://mlsanity.com/paper/2208.09163/) (2022)
- [Detecting Narrative Elements in Informational Text](https://mlsanity.com/paper/2210.03028/) (2022)
- [Building Context-aware Clause Representations for Situation Entity Type Classification](https://mlsanity.com/paper/1809.07483/) (2018)
- [A Novel Corpus of Discourse Structure in Humans and Computers](https://mlsanity.com/paper/2111.05940/) (2021)
- [causalgraph: A Python Package for Modeling, Persisting and Visualizing Causal Graphs Embedded in Knowledge Graphs](https://mlsanity.com/paper/2301.08490/) (2023)
- [Enhancing Event Extraction from Short Stories through Contextualized Prompts](https://mlsanity.com/paper/2412.10745/) (2024)

## Built on by (most cited first, 2 of 2)

- [LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery](https://mlsanity.com/paper/2506.00844/) (2025)
- [A Counterfactual Graph Approach to Oppositional Narrative Analysis](https://mlsanity.com/paper/2603.06135/) (2026)

## Abstract (arXiv)

We propose a novel framework for generating causal graphs from narrative texts, bridging high-level causality and detailed event-specific relationships. Our method first extracts concise, agent-centered vertices using large language model (LLM)-based summarization. We introduce an "Expert Index," comprising seven linguistically informed features, integrated into a Situation-Task-Action-Consequence (STAC) classification model. This hybrid system, combining RoBERTa embeddings with the Expert Index, achieves superior precision in causal link identification compared to pure LLM-based approaches. Finally, a structured five-iteration prompting process refines and constructs connected causal graphs. Experiments on 100 narrative chapters and short stories demonstrate that our approach consistently outperforms GPT-4o and Claude 3.5 in causal graph quality, while maintaining readability. The open-source tool provides an interpretable, efficient solution for capturing nuanced causal chains in narratives.