2023
DOI: 10.1039/d3dd00019b
|View full text |Cite
|
Sign up to set email alerts
|

Extracting structured seed-mediated gold nanorod growth procedures from scientific text with LLMs

Nicholas Walker,
Sanghoon Lee,
John Dagdelen
et al.

Abstract: Although gold nanorods have been the subject of much research, the pathways for controlling their shape and thereby their optical properties remain largely heuristically understood. Although it is apparent that...

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
5
0

Year Published

2023
2023
2025
2025

Publication Types

Select...
7

Relationship

1
6

Authors

Journals

citations
Cited by 11 publications
(5 citation statements)
references
References 72 publications
0
5
0
Order By: Relevance
“…Despite the convenience of these methods, they are not perfect and tend to struggle with complex synthesis extraction and procedure-outcome linking. Addressing these problems is becoming more approachable with the proliferation of new large language models like GPT-3, which has been proven useful in creating materials science chatbot assistants, the extraction of complex synthesis procedures for gold nanorods, and structured information extraction of materials properties, structure, and application. , Nonetheless, analyses performed on our manually curated dataset represent an upper limit of what can be learned through literature mining alone for the end-to-end synthesis pathways of a particular material.…”
Section: Discussionmentioning
confidence: 99%
“…Despite the convenience of these methods, they are not perfect and tend to struggle with complex synthesis extraction and procedure-outcome linking. Addressing these problems is becoming more approachable with the proliferation of new large language models like GPT-3, which has been proven useful in creating materials science chatbot assistants, the extraction of complex synthesis procedures for gold nanorods, and structured information extraction of materials properties, structure, and application. , Nonetheless, analyses performed on our manually curated dataset represent an upper limit of what can be learned through literature mining alone for the end-to-end synthesis pathways of a particular material.…”
Section: Discussionmentioning
confidence: 99%
“…A recent study on gold nanorod growth procedures also demonstrated the ability of LLM in a similar task. 82 In contrast to the LIFT-based prediction of atomization energies reported in the first section by the Berkeley–Madison team, parameter-efficient fine-tuning of the open-source Alpaca model 86–88 using LoRA 48 did not yield a model that can construct valid JSONs.…”
Section: Introductionmentioning
confidence: 92%
“…To facilitate downstream use of the information, LLMs can also convert unstructured data—the typical form of these literature reports—into structured data. The use of GPT for this application has been reported by Dunn et al 81 and Walker et al , 82 who used an iterative fine-tuning approach to extract data structured in JSON from papers. In their approach, initial (zero-shot) completions of the LLM are corrected by domain experts.…”
Section: Introductionmentioning
confidence: 99%
“…Recently, LLMs have also been successfully applied to extract synthesis parameters from chemistry and materials science literature. 25–29…”
Section: Introductionmentioning
confidence: 99%