GrapheneChat: A Large Language Model for Enhancing Graphene Research.
| Title: | GrapheneChat: A Large Language Model for Enhancing Graphene Research. |
|---|---|
| Authors: | Yang D; State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310058, China.; Lu C; State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310058, China.; Feng Y; State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310058, China.; College of Mechanical Engineering, Guizhou University, Guiyang 550025, China.; Mao W; State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310058, China.; Wang K; State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310058, China.; Sun L; Center for Nanochemistry, Beijing Science and Engineering Center for Nanocarbons, Beijing National Laboratory for Molecular Sciences, College of Chemistry and Molecular Engineering, Peking University, Beijing 100871, China.; Beijing Graphene Institute, Beijing 100095, China.; Wang Y; Department of Materials Science & Metallurgy, University of Cambridge, 27 Charles Babbage Road, Cambridge CB3 0FS, U.K.; Hu B; State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310058, China.; Tan J; State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310058, China.; Liu Z; Center for Nanochemistry, Beijing Science and Engineering Center for Nanocarbons, Beijing National Laboratory for Molecular Sciences, College of Chemistry and Molecular Engineering, Peking University, Beijing 100871, China.; Beijing Graphene Institute, Beijing 100095, China.; Song X; State Key Laboratory of Fluid Power & Mechatronic Systems, Zhejiang University, Hangzhou 310058, China. |
| Source: | ACS nano [ACS Nano] 2026 Mar 31; Vol. 20 (12), pp. 9970-9982. Date of Electronic Publication: 2026 Mar 13. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: American Chemical Society Country of Publication: United States NLM ID: 101313589 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1936-086X (Electronic) Linking ISSN: 19360851 NLM ISO Abbreviation: ACS Nano Subsets: MEDLINE; PubMed not MEDLINE |
| Imprint Name(s): | Original Publication: Washington D.C. : American Chemical Society |
| Abstract: | Graphene has garnered significant multidisciplinary interest for its exceptional properties and wide-ranging applications in materials science, engineering, physics, energy storage, and electronics. However, integrating the vast and heterogeneous body of knowledge into cohesive interdisciplinary research remains significantly challenging, requiring highly specialized expertise, rigorous experimental design, and efficient literature knowledge retrieval. To address these issues, GrapheneChat was developed as the first fine-tuned large language model (LLM) specifically designed for graphene research. Trained on comprehensive data sets of monographs and scholarly articles, GrapheneChat employs a two-stage strategy of supervised fine-tuning (SFT) and direct preference optimization (DPO) to achieve enhanced domain-specific reasoning and experimental design. By integrating a retrieval-augmented generation (RAG) framework, the model delivers literature-grounded and reference-supported responses for knowledge retrieval. Quantitative evaluations using the newly developed GrapheneBench demonstrate that GrapheneChat achieves an impressive accuracy of 91%, comparable to state-of-the-art models like GPT-4, while requiring fewer computational resources. As an intelligent research assistant, GrapheneChat not only facilitates interdisciplinary innovation but also establishes a paradigm for building domain-specific LLMs that enhance expert productivity in literature mining. |
| Contributed Indexing: | Keywords: fine-tuning; graphene; knowledge retrieval; large language model; retrieval-augmented generation |
| Entry Date(s): | Date Created: 20260313 Latest Revision: 20260331 |
| Update Code: | 20260331 |
| DOI: | 10.1021/acsnano.5c21335 |
| PMID: | 41823254 |
| Database: | MEDLINE |
Journal Article