# Narrating Causal Graphs with Large Language Models

arXiv: https://arxiv.org/abs/2403.07118 · HTML: https://mlsanity.com/paper/2403.07118/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 11 Mar 2024.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA](https://mlsanity.com/paper/2109.05014/) (2021)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT](https://mlsanity.com/paper/2304.08448/) (2023)
- [A Causal Lens for Controllable Text Generation](https://mlsanity.com/paper/2201.09119/) (2022)
- [GPT-too: A language-model-first approach for AMR-to-text generation](https://mlsanity.com/paper/2005.09123/) (2020)
- [GPT-3 Models are Poor Few-Shot Learners in the Biomedical Domain](https://mlsanity.com/paper/2109.02555/) (2021)
- [Guided Generation of Cause and Effect](https://mlsanity.com/paper/2107.09846/) (2021)
- [Few-shot Knowledge Graph-to-Text Generation with Pretrained Language Models](https://mlsanity.com/paper/2106.01623/) (2021)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [Artificial Intelligence is stupid and causal reasoning won't fix it](https://mlsanity.com/paper/2008.07371/) (2020)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Promoting Graph Awareness in Linearized Graph-to-Text Generation](https://mlsanity.com/paper/2012.15793/) (2020)
- [ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models](https://mlsanity.com/paper/2210.04325/) (2022)
- [Empathetic Response Generation through Graph-based Multi-hop Reasoning on Emotional Causality](https://mlsanity.com/paper/2110.04614/) (2021)

## Built on by (most cited first, 4 of 4)

- [Causality for Large Language Models](https://mlsanity.com/paper/2410.15319/) (2024)
- [Clinical Insights: A Comprehensive Review of Language Models in Medicine](https://mlsanity.com/paper/2408.11735/) (2024)
- [A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges](https://mlsanity.com/paper/2602.05883/) (2026)
- [Causal Graph based Event Reasoning using Semantic Relation Experts](https://mlsanity.com/paper/2506.06910/) (2025)

## Abstract (arXiv)

The use of generative AI to create text descriptions from graphs has mostly focused on knowledge graphs, which connect concepts using facts. In this work we explore the capability of large pretrained language models to generate text from causal graphs, where salient concepts are represented as nodes and causality is represented via directed, typed edges. The causal reasoning encoded in these graphs can support applications as diverse as healthcare or marketing. Using two publicly available causal graph datasets, we empirically investigate the performance of four GPT-3 models under various settings. Our results indicate that while causal text descriptions improve with training data, compared to fact-based graphs, they are harder to generate under zero-shot settings. Results further suggest that users of generative AI can deploy future applications faster since similar performances are obtained when training a model with only a few examples as compared to fine-tuning via a large curated dataset.