# Implicit Causal Graph Construction in Text via Chain Discovery

arXiv: https://arxiv.org/abs/2606.07525 · HTML: https://mlsanity.com/paper/2606.07525/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 20 Apr 2026.

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

- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Causal Discovery with Language Models as Imperfect Experts](https://mlsanity.com/paper/2307.02390/) (2023)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?](https://mlsanity.com/paper/2506.21215/) (2025)
- [Guided Generation of Cause and Effect](https://mlsanity.com/paper/2107.09846/) (2021)
- [Zero-shot Causal Graph Extrapolation from Text via LLMs](https://mlsanity.com/paper/2312.14670/) (2023)
- [CausalKG: Causal Knowledge Graph Explainability using interventional and counterfactual reasoning](https://mlsanity.com/paper/2201.03647/) (2022)
- [Identifying while Learning for Document Event Causality Identification](https://mlsanity.com/paper/2405.20608/) (2024)
- [ACCESS : A Benchmark for Abstract Causal Event Discovery and Reasoning](https://mlsanity.com/paper/2502.08148/) (2025)
- [Causal Graph based Event Reasoning using Semantic Relation Experts](https://mlsanity.com/paper/2506.06910/) (2025)
- [IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular Data](https://mlsanity.com/paper/2510.09217/) (2025)
- [Assessing LLM Reasoning Through Implicit Causal Chain Discovery in Climate Discourse](https://mlsanity.com/paper/2510.13417/) (2025)
- [ClimateCause: Complex and Implicit Causal Structures in Climate Reports](https://mlsanity.com/paper/2604.14856/) (2026)

## Abstract (arXiv)

Causal graphs in text are typically populated by observable, predefined events. In contrast, we study implicit causal graph construction from text by treating each described cause-effect pair as the begin- and endpoint of an underlying latent causal graph and using large language models (LLMs) to infer intermediate causal events. We compare end-to-end graph construction with methods that frame the task as causal chain discovery. In the latter, graphs are built either by aggregating inferred chains or by progressively expanding partial chains through an iterative search process. We further explore Wisdom of the Crowd extensions that access causal knowledge from multiple LLMs in post-hoc aggregation and collaborative inference settings. We analyze trade-offs among these approaches and evaluate the validity of inferred causal relations using a manually curated database of 1,560 scientifically validated causal pairs. This database-based evaluation is proposed as reliable, resource-efficient, and transferable to settings where ground-truth graphs are unavailable.