Causal Discovery from Data Assisted by Large Language Models
Knowledge driven discovery of novel materials necessitates the development of the causal models for the property emergence. While in classical physical paradigm the causal relationships are deduced based on the physical principles or via experiment, rapid accumulation of observational data necessitates learning causal relationships between dissimilar aspects of materials structure and functionalities based on observations. For this, it is essential to integrate experimental data with prior domain knowledge. Here we demonstrate this approach by combining high-resolution scanning transmission electron microscopy (STEM) data with insights derived from large language models (LLMs). By fine-tuning ChatGPT on domain-specific literature, such as arXiv papers on ferroelectrics, and combining obtained information with data-driven causal discovery, we construct adjacency matrices for Directed Acyclic Graphs (DAGs) that map the causal relationships between structural, chemical, and polarization degrees of freedom in Sm-doped BiFeO3 (SmBFO). This approach enables us to hypothesize how synthesis conditions influence material properties, particularly the coercive field (E0), and guides experimental validation. The ultimate objective of this work is to develop a unified framework that integrates LLM-driven literature analysis with data-driven discovery, facilitating the precise engineering of ferroelectric materials by establishing clear connections between synthesis conditions and their resulting material properties.
Code (0)
등록된 구현이 없습니다.
Tasks
Causal DiscoverySimilar Papers 제목 키워드 기반
A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery
The increasing use of large language models (LLMs) in causal discovery as a substitute for human domain experts highlights the need for optimal model selection. This paper presents the first hallucination survey of popul…
Causal DiscoveryHallucinationLanguage ModelingLanguage Modelling+5Causal Discovery in the Era of Agents
Recent attempts to combine large language models (LLMs) with causal discovery ask models to infer pairwise directions, propose graph structures, or inject language-model outputs as priors and constraints. These approache…
LLM-Assisted Causal Structure Disambiguation and Factor Extraction for Legal Judgment Prediction
Mainstream methods for Legal Judgment Prediction (LJP) based on Pre-trained Language Models (PLMs) heavily rely on the statistical correlation between case facts and judgment results. This paradigm lacks explicit modelin…
Causal InferenceARIA: A Causal-Aware Framework for Rescuing LLM Reasoning in Trustworthy Materials Discovery
Generative models have revolutionized the process of materials discovery, yet they often fail to satisfy underlying physical causality. Through an analysis of Large Language Models (LLMs) augmented with knowledge graphs …
Knowledge GraphsFrom Pre-training Corpora to Large Language Models: What Factors Influence LLM Performance in Causal Discovery Tasks?
Recent advances in artificial intelligence have seen Large Language Models (LLMs) demonstrate notable proficiency in causal discovery tasks. This study explores the factors influencing the performance of LLMs in causal d…
Causal Discovery