Mining experimental data from Materials Science literature with Large Language Models: an evaluation study

• URL: http://arxiv.org/abs/2401.11052v3
• Date: Thu, 30 May 2024 20:28:08 GMT
• Title: Mining experimental data from Materials Science literature with Large Language Models: an evaluation study
• Authors: Luca Foppiano, Guillaume Lambard, Toshiyuki Amagasa, Masashi Ishii,
• Abstract summary: This study is dedicated to assessing the capabilities of large language models (LLMs) in extracting structured information from scientific documents in materials science. We focus on two critical tasks of information extraction: (i) a named entity recognition (NER) of studied materials and physical properties and (ii) a relation extraction (RE) between these entities. The performance of LLMs in executing these tasks is benchmarked against traditional models based on the BERT architecture and rule-based approaches (baseline)
• Score: 1.9849264945671101
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study is dedicated to assessing the capabilities of large language models (LLMs) such as GPT-3.5-Turbo, GPT-4, and GPT-4-Turbo in extracting structured information from scientific documents in materials science. To this end, we primarily focus on two critical tasks of information extraction: (i) a named entity recognition (NER) of studied materials and physical properties and (ii) a relation extraction (RE) between these entities. Due to the evident lack of datasets within Materials Informatics (MI), we evaluated using SuperMat, based on superconductor research, and MeasEval, a generic measurement evaluation corpus. The performance of LLMs in executing these tasks is benchmarked against traditional models based on the BERT architecture and rule-based approaches (baseline). We introduce a novel methodology for the comparative analysis of intricate material expressions, emphasising the standardisation of chemical formulas to tackle the complexities inherent in materials science information assessment. For NER, LLMs fail to outperform the baseline with zero-shot prompting and exhibit only limited improvement with few-shot prompting. However, a GPT-3.5-Turbo fine-tuned with the appropriate strategy for RE outperforms all models, including the baseline. Without any fine-tuning, GPT-4 and GPT-4-Turbo display remarkable reasoning and relationship extraction capabilities after being provided with merely a couple of examples, surpassing the baseline. Overall, the results suggest that although LLMs demonstrate relevant reasoning skills in connecting concepts, specialised models are currently a better choice for tasks requiring extracting complex domain-specific entities like materials. These insights provide initial guidance applicable to other materials science sub-domains in future work.

Related papers

• Evaluating Large Language Models for Structured Science Summarization in the Open Research Knowledge Graph [18.41743815836192]
  We propose using Large Language Models (LLMs) to automatically suggest properties for structured science summaries. Our study performs a comprehensive comparative analysis between ORKG's manually curated properties and those generated by the aforementioned state-of-the-art LLMs. Overall, LLMs show potential as recommendation systems for structuring science, but further finetuning is recommended to improve their alignment with scientific tasks and mimicry of human expertise.
  arXiv  Detail & Related papers  (2024-05-03T14:03:04Z)
• Learning to Extract Structured Entities Using Language Models [52.281701191329]
  Recent advances in machine learning have significantly impacted the field of information extraction. We reformulate the task to be entity-centric, enabling the use of diverse metrics. We contribute to the field by introducing Structured Entity Extraction and proposing the Approximate Entity Set OverlaP metric.
  arXiv  Detail & Related papers  (2024-02-06T22:15:09Z)
• Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data? [49.688233418425995]
  Struc-Bench is a comprehensive benchmark featuring prominent Large Language Models (LLMs) We propose two innovative metrics, P-Score (Prompting Score) and H-Score (Heuristical Score) Our experiments show that applying our structure-aware fine-tuning to LLaMA-7B leads to substantial performance gains.
  arXiv  Detail & Related papers  (2023-09-16T11:31:58Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• Accelerated materials language processing enabled by GPT [5.518792725397679]
  We develop generative transformer (GPT)-enabled pipelines for materials language processing. First, we develop a GPT-enabled document classification method for screening relevant documents. Secondly, for NER task, we design an entity-centric prompts, and learning few-shot of them improved the performance. Finally, we develop an GPT-enabled extractive QA model, which provides improved performance and shows the possibility of automatically correcting annotations.
  arXiv  Detail & Related papers  (2023-08-18T07:31:13Z)
• MaScQA: A Question Answering Dataset for Investigating Materials Science Knowledge of Large Language Models [29.70397245624547]
  This work curates a dataset of 650 challenging questions from the materials domain that require the knowledge and skills of a materials student. It is observed that GPT-4 gives the best performance (62% accuracy) as compared to GPT-3.5.
  arXiv  Detail & Related papers  (2023-08-17T17:51:05Z)
• Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks [90.11273439036455]
  Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks. We propose Knowledge-Augmented Reasoning Distillation (KARD), a novel method that fine-tunes small LMs to generate rationales from LLMs with augmented knowledge retrieved from an external knowledge base. We empirically show that KARD significantly improves the performance of small T5 and GPT models on the challenging knowledge-intensive reasoning datasets.
  arXiv  Detail & Related papers  (2023-05-28T13:00:00Z)
• LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities [66.36633042421387]
  Large Language Models (LLMs) for Knowledge Graph (KG) construction and reasoning evaluated. We propose AutoKG, a multi-agent-based approach employing LLMs and external sources for KG construction and reasoning.
  arXiv  Detail & Related papers  (2023-05-22T15:56:44Z)
• Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT [9.33544942080883]
  This article presents a new natural language processing (NLP) task called structured information inference (SII) to address the complexities of information extraction at the device level in materials science. We accomplished this task by tuning GPT-3 on an existing perovskite solar cell FAIR dataset with 91.8% F1-score and extended the dataset with data published since its release. We also designed experiments to predict the electrical performance of solar cells and design materials or devices with targeted parameters using large language models (LLMs)
  arXiv  Detail & Related papers  (2023-04-05T04:01:52Z)
• Information Extraction in Low-Resource Scenarios: Survey and Perspective [56.5556523013924]
  Information Extraction seeks to derive structured information from unstructured texts. This paper presents a review of neural approaches to low-resource IE from emphtraditional and emphLLM-based perspectives.
  arXiv  Detail & Related papers  (2022-02-16T13:44:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.