Dynamic in-context learning with conversational models for data extraction and materials property prediction
The advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that lev...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2025-03-01
|
| Series: | APL Machine Learning |
| Online Access: | http://dx.doi.org/10.1063/5.0254406 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850259667441156096 |
|---|---|
| author | Chinedu E. Ekuma |
| author_facet | Chinedu E. Ekuma |
| author_sort | Chinedu E. Ekuma |
| collection | DOAJ |
| description | The advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that leverages advanced conversational LLMs such as Google gemini-pro and OpenAI gpt-4, blends zero-shot with few-shot in-context learning, and employs engineered prompts for the dynamic refinement of structured information hierarchies—enabling autonomous, efficient, scalable, and accurate identification, extraction, and verification of material property data. Our tests on material data demonstrate precision and recall that exceed 95% with an error rate of ∼9%, highlighting the effectiveness and versatility of the toolkit. Finally, databases for 2D material thicknesses, a critical parameter for device integration, and energy bandgap values are developed using PropertyExtractor. In particular, for the thickness database, the rapid evolution of the field has outpaced both experimental measurements and computational methods, creating a significant data gap. Our work addresses this gap and showcases the potential of PropertyExtractor as a reliable and efficient tool for the autonomous generation of various material property databases, advancing the field. |
| format | Article |
| id | doaj-art-13b70add299a4d66afaae18e0cfffe3c |
| institution | OA Journals |
| issn | 2770-9019 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Machine Learning |
| spelling | doaj-art-13b70add299a4d66afaae18e0cfffe3c2025-08-20T01:55:49ZengAIP Publishing LLCAPL Machine Learning2770-90192025-03-0131016119016119-910.1063/5.0254406Dynamic in-context learning with conversational models for data extraction and materials property predictionChinedu E. Ekuma0Department of Physics, Lehigh University, Bethlehem, Pennsylvania 18015, USAThe advent of natural language processing and large language models (LLMs) has revolutionized the extraction of data from unstructured scholarly papers. However, ensuring data trustworthiness remains a significant challenge. In this paper, we introduce PropertyExtractor, an open-source tool that leverages advanced conversational LLMs such as Google gemini-pro and OpenAI gpt-4, blends zero-shot with few-shot in-context learning, and employs engineered prompts for the dynamic refinement of structured information hierarchies—enabling autonomous, efficient, scalable, and accurate identification, extraction, and verification of material property data. Our tests on material data demonstrate precision and recall that exceed 95% with an error rate of ∼9%, highlighting the effectiveness and versatility of the toolkit. Finally, databases for 2D material thicknesses, a critical parameter for device integration, and energy bandgap values are developed using PropertyExtractor. In particular, for the thickness database, the rapid evolution of the field has outpaced both experimental measurements and computational methods, creating a significant data gap. Our work addresses this gap and showcases the potential of PropertyExtractor as a reliable and efficient tool for the autonomous generation of various material property databases, advancing the field.http://dx.doi.org/10.1063/5.0254406 |
| spellingShingle | Chinedu E. Ekuma Dynamic in-context learning with conversational models for data extraction and materials property prediction APL Machine Learning |
| title | Dynamic in-context learning with conversational models for data extraction and materials property prediction |
| title_full | Dynamic in-context learning with conversational models for data extraction and materials property prediction |
| title_fullStr | Dynamic in-context learning with conversational models for data extraction and materials property prediction |
| title_full_unstemmed | Dynamic in-context learning with conversational models for data extraction and materials property prediction |
| title_short | Dynamic in-context learning with conversational models for data extraction and materials property prediction |
| title_sort | dynamic in context learning with conversational models for data extraction and materials property prediction |
| url | http://dx.doi.org/10.1063/5.0254406 |
| work_keys_str_mv | AT chinedueekuma dynamicincontextlearningwithconversationalmodelsfordataextractionandmaterialspropertyprediction |