# Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery

arXiv: https://arxiv.org/abs/2407.18752 · HTML: https://mlsanity.com/paper/2407.18752/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 50 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners](https://mlsanity.com/paper/2009.07118/) (2020)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [Large Language Models are Few-Shot Clinical Information Extractors](https://mlsanity.com/paper/2205.12689/) (2022)
- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [Understanding Causality with Large Language Models: Feasibility and Opportunities](https://mlsanity.com/paper/2304.05524/) (2023)
- [Causal-Discovery Performance of ChatGPT in the context of Neuropathic Pain Diagnosis](https://mlsanity.com/paper/2301.13819/) (2023)
- [Generative Prompt Tuning for Relation Classification](https://mlsanity.com/paper/2210.12435/) (2022)
- [MIMICause: Representation and automatic extraction of causal relation types from clinical notes](https://mlsanity.com/paper/2110.07090/) (2021)

## Built on by (most cited first, 3 of 3)

- [Can LLMs Leverage Observational Data? Towards Data-Driven Causal Discovery with LLMs](https://mlsanity.com/paper/2504.10936/) (2025)
- [Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts](https://mlsanity.com/paper/2509.04982/) (2025)
- [DKCD: Domain Knowledge-Enhanced Causal Discovery from Unstructured Data](https://mlsanity.com/paper/2607.09348/) (2026)

## Abstract (arXiv)

Causal discovery aims to estimate causal structures among variables based on observational data. Large Language Models (LLMs) offer a fresh perspective to tackle the causal discovery problem by reasoning on the metadata associated with variables rather than their actual data values, an approach referred to as knowledge-based causal discovery. In this paper, we investigate the capabilities of Small Language Models (SLMs, defined as LLMs with fewer than 1 billion parameters) with prompt-based learning for knowledge-based causal discovery. Specifically, we present KG Structure as Prompt, a novel approach for integrating structural information from a knowledge graph, such as common neighbor nodes and metapaths, into prompt-based learning to enhance the capabilities of SLMs. Experimental results on three types of biomedical and open-domain datasets under few-shot settings demonstrate the effectiveness of our approach, surpassing most baselines and even conventional fine-tuning approaches trained on full datasets. Our findings further highlight the strong capabilities of SLMs: in combination with knowledge graphs and prompt-based learning, SLMs demonstrate the potential to surpass LLMs with larger number of parameters. Our code and datasets are available on GitHub.