Domain-specific chatbots for science using embeddings

Yager, Kevin G.

doi:10.1039/D3DD00112A

Title: Domain-specific chatbots for science using embeddings

Journal Article · Mon Dec 04 00:00:00 EST 2023 · Digital Discovery

DOI:https://doi.org/10.1039/D3DD00112A· OSTI ID:2202517

^[1]

Center for Functional Nanomaterials, Brookhaven National Laboratory, Upton, New York 11973, USA

Large language models (LLMs) have emerged as powerful machine-learning systems capable of handling a myriad of tasks. Tuned versions of these systems have been turned into chatbots that can respond to user queries on a vast diversity of topics, providing informative and creative replies. However, their application to physical science research remains limited owing to their incomplete knowledge in these areas, contrasted with the needs of rigor and sourcing in science domains. Here, we demonstrate how existing methods and software tools can be easily combined to yield a domain-specific chatbot. The system ingests scientific documents in existing formats and uses text embedding lookup to provide the LLM with domain-specific contextual information when composing its reply. We similarly demonstrate that existing image embedding methods can be used for search and retrieval across publication figures. These results confirm that LLMs are already suitable for use by physical scientists in accelerating their research efforts.

View Journal Article

Cite

Export

Save

Research Organization:: Brookhaven National Laboratory (BNL), Upton, NY (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)

Grant/Contract Number:: SC0012704

OSTI ID:: 2202517

Alternate ID(s):: OSTI ID: 2267566

Report Number(s):: BNL-225132-2023-JAAM; DDIIAI

Journal Information:: Digital Discovery, Journal Name: Digital Discovery Vol. 2 Journal Issue: 6; ISSN 2635-098X

Publisher:: Royal Society of Chemistry (RSC)Copyright Statement

Country of Publication:: United Kingdom

Language:: English

References (63)

What learning algorithm is in-context learning? Investigations with linear models Akyürek, Ekin; Schuurmans, Dale; Andreas, Jacob arXiv https://doi.org/10.48550/arXiv.2211.15661	preprint	January 2022
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting Qin, Zhen; Jagerman, Rolf; Hui, Kai arXiv https://doi.org/10.48550/arXiv.2306.17563	preprint	January 2023
Sparks of Artificial General Intelligence: Early experiments with GPT-4 Bubeck, Sébastien; Chandrasekaran, Varun; Eldan, Ronen arXiv https://doi.org/10.48550/arXiv.2303.12712	preprint	January 2023
TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs Liang, Yaobo; Wu, Chenfei; Song, Ting arXiv https://doi.org/10.48550/arXiv.2303.16434	preprint	January 2023
CERMINE: automatic extraction of structured metadata from scientific literature Tkaczyk, Dominika; Szostek, Paweł; Fedoryszak, Mateusz International Journal on Document Analysis and Recognition (IJDAR), Vol. 18, Issue 4 https://doi.org/10.1007/s10032-015-0249-8	journal	July 2015
ReAct: Synergizing Reasoning and Acting in Language Models Yao, Shunyu; Zhao, Jeffrey; Yu, Dian arXiv https://doi.org/10.48550/arXiv.2210.03629	preprint	January 2022
CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society Li, Guohao; Hammoud, Hasan Abed Al Kader; Itani, Hani arXiv https://doi.org/10.48550/arXiv.2303.17760	preprint	January 2023
QLoRA: Efficient Finetuning of Quantized LLMs Dettmers, Tim; Pagnoni, Artidoro; Holtzman, Ari arXiv https://doi.org/10.48550/arXiv.2305.14314	preprint	January 2023
On the Opportunities and Risks of Foundation Models Bommasani, Rishi; Hudson, Drew A.; Adeli, Ehsan arXiv https://doi.org/10.48550/arXiv.2108.07258	preprint	January 2021
Autonomous experimentation systems for materials development: A community perspective Stach, Eric; DeCost, Brian; Kusne, A. Gilad Matter, Vol. 4, Issue 9 https://doi.org/10.1016/j.matt.2021.06.036	journal	September 2021
High-Resolution Image Synthesis with Latent Diffusion Models Rombach, Robin; Blattmann, Andreas; Lorenz, Dominik arXiv https://doi.org/10.48550/arXiv.2112.10752	preprint	January 2021
Molecular Origin of Photovoltaic Performance in Donor- block -Acceptor All-Conjugated Block Copolymers Smith, Kendall A.; Lin, Yen-Hao; Mok, Jorge W. Macromolecules, Vol. 48, Issue 22 https://doi.org/10.1021/acs.macromol.5b01383	journal	October 2015
Fine-Tuning Language Models from Human Preferences Ziegler, Daniel M.; Stiennon, Nisan; Wu, Jeffrey arXiv https://doi.org/10.48550/arXiv.1909.08593	preprint	January 2019
Generative Artificial Intelligence: Trends and Prospects Jovanovic, Mladan; Campbell, Mark Computer, Vol. 55, Issue 10 https://doi.org/10.1109/MC.2022.3192720	journal	October 2022
Emergent analogical reasoning in large language models Webb, Taylor; Holyoak, Keith J.; Lu, Hongjing Nature Human Behaviour, Vol. 7, Issue 9 https://doi.org/10.1038/s41562-023-01659-w	journal	July 2023
Large Language Models are Zero-Shot Reasoners Kojima, Takeshi; Gu, Shixiang Shane; Reid, Machel arXiv https://doi.org/10.48550/arXiv.2205.11916	preprint	January 2022
Autonomous discovery of emergent morphologies in directed self-assembly of block copolymer blends Doerk, Gregory S.; Stein, Aaron; Bae, Suwon Science Advances, Vol. 9, Issue 2 https://doi.org/10.1126/sciadv.add3687	journal	January 2023
Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback Peng, Baolin; Galley, Michel; He, Pengcheng arXiv https://doi.org/10.48550/arXiv.2302.12813	preprint	January 2023
LoRA: Low-Rank Adaptation of Large Language Models Hu, Edward J.; Shen, Yelong; Wallis, Phillip arXiv https://doi.org/10.48550/arXiv.2106.09685	preprint	January 2021
Artificial muses: Generative Artificial Intelligence Chatbots Have Risen to Human-Level Creativity Haase, Jennifer; Hanel, Paul H. P. arXiv https://doi.org/10.48550/arXiv.2303.12003	preprint	January 2023
Emergent Abilities of Large Language Models Wei, Jason; Tay, Yi; Bommasani, Rishi arXiv https://doi.org/10.48550/arXiv.2206.07682	preprint	January 2022
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task Li, Kenneth; Hopkins, Aspen K.; Bau, David arXiv https://doi.org/10.48550/arXiv.2210.13382	preprint	January 2022
Lamellar and liquid crystal ordering in solvent-annealed all-conjugated block copolymers Lin, Yen-Hao; Yager, Kevin G.; Stewart, Bridget Soft Matter, Vol. 10, Issue 21 https://doi.org/10.1039/C3SM53090F	journal	January 2014
Autonomous materials discovery driven by Gaussian process regression with inhomogeneous measurement noise and anisotropic kernels Noack, Marcus M.; Doerk, Gregory S.; Li, Ruipeng Scientific Reports, Vol. 10, Issue 1 https://doi.org/10.1038/s41598-020-74394-1	journal	October 2020
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face Shen, Yongliang; Song, Kaitao; Tan, Xu arXiv https://doi.org/10.48550/arXiv.2303.17580	preprint	January 2023
ChatGPT is not all you need. A State of the Art Review of large Generative AI models Gozalo-Brizuela, Roberto; Garrido-Merchan, Eduardo C. arXiv https://doi.org/10.48550/arXiv.2301.04655	preprint	January 2023
Toolformer: Language Models Can Teach Themselves to Use Tools Schick, Timo; Dwivedi-Yu, Jane; Dessì, Roberto arXiv https://doi.org/10.48550/arXiv.2302.04761	preprint	January 2023
TruthfulQA: Measuring How Models Mimic Human Falsehoods Lin, Stephanie; Hilton, Jacob; Evans, Owain arXiv https://doi.org/10.48550/arXiv.2109.07958	preprint	January 2021
Focused Transformer: Contrastive Training for Context Scaling Tworkowski, Szymon; Staniszewski, Konrad; Pacek, Mikołaj arXiv https://doi.org/10.48550/arXiv.2307.03170	preprint	January 2023
Tree of Thoughts: Deliberate Problem Solving with Large Language Models Yao, Shunyu; Yu, Dian; Zhao, Jeffrey arXiv https://doi.org/10.48550/arXiv.2305.10601	preprint	January 2023
Progress and prospects for accelerating materials science with automated and autonomous workflows Stein, Helge S.; Gregoire, John M. Chemical Science, Vol. 10, Issue 42 https://doi.org/10.1039/C9SC03766G	journal	January 2019
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models Xu, Binfeng; Peng, Zhiyuan; Lei, Bowen arXiv https://doi.org/10.48550/arXiv.2305.18323	preprint	January 2023
LongNet: Scaling Transformers to 1,000,000,000 Tokens Ding, Jiayu; Ma, Shuming; Dong, Li arXiv https://doi.org/10.48550/arXiv.2307.02486	preprint	January 2023
Novel photo-switching using azobenzene functional materials Yager, Kevin G.; Barrett, Christopher J. Journal of Photochemistry and Photobiology A: Chemistry, Vol. 182, Issue 3 https://doi.org/10.1016/j.jphotochem.2006.04.021	journal	September 2006
Reflexion: Language Agents with Verbal Reinforcement Learning Shinn, Noah; Cassano, Federico; Berman, Edward arXiv https://doi.org/10.48550/arXiv.2303.11366	preprint	January 2023
Hierarchical Text-Conditional Image Generation with CLIP Latents Ramesh, Aditya; Dhariwal, Prafulla; Nichol, Alex arXiv https://doi.org/10.48550/arXiv.2204.06125	preprint	January 2022
Galactica: A Large Language Model for Science Taylor, Ross; Kardas, Marcin; Cucurull, Guillem arXiv https://doi.org/10.48550/arXiv.2211.09085	preprint	January 2022
Emergent autonomous scientific research capabilities of large language models Boiko, Daniil A.; MacKnight, Robert; Gomes, Gabe arXiv https://doi.org/10.48550/arXiv.2304.05332	preprint	January 2023
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge Clark, Peter; Cowhey, Isaac; Etzioni, Oren arXiv https://doi.org/10.48550/arXiv.1803.05457	preprint	January 2018
Theory of Mind Might Have Spontaneously Emerged in Large Language Models Kosinski, Michal arXiv https://doi.org/10.48550/arXiv.2302.02083	preprint	January 2023
Longformer: The Long-Document Transformer Beltagy, Iz; Peters, Matthew E.; Cohan, Arman arXiv https://doi.org/10.48550/arXiv.2004.05150	preprint	January 2020
HellaSwag: Can a Machine Really Finish Your Sentence? Zellers, Rowan; Holtzman, Ari; Bisk, Yonatan arXiv https://doi.org/10.48550/arXiv.1905.07830	preprint	January 2019
Learning Transferable Visual Models From Natural Language Supervision Radford, Alec; Kim, Jong Wook; Hallacy, Chris arXiv https://doi.org/10.48550/arXiv.2103.00020	preprint	January 2021
Learning to Generate Novel Scientific Directions with Contextualized Literature-based Discovery Wang, Qingyun; Downey, Doug; Ji, Heng arXiv https://doi.org/10.48550/arXiv.2305.14259	preprint	January 2023
Non-native three-dimensional block copolymer morphologies Rahman, Atikur; Majewski, Pawel W.; Doerk, Gregory Nature Communications, Vol. 7, Issue 1 https://doi.org/10.1038/ncomms13988	journal	December 2016
Attention Is All You Need Vaswani, Ashish; Shazeer, Noam; Parmar, Niki arXiv https://doi.org/10.48550/arXiv.1706.03762	preprint	January 2017
Progress measures for grokking via mechanistic interpretability Nanda, Neel; Chan, Lawrence; Lieberum, Tom arXiv https://doi.org/10.48550/arXiv.2301.05217	preprint	January 2023
Measuring Massive Multitask Language Understanding Hendrycks, Dan; Burns, Collin; Basart, Steven arXiv https://doi.org/10.48550/arXiv.2009.03300	preprint	January 2020
Large Language Models as Tool Makers Cai, Tianle; Wang, Xuezhi; Ma, Tengyu arXiv https://doi.org/10.48550/arXiv.2305.17126	preprint	January 2023
Let's Verify Step by Step Lightman, Hunter; Kosaraju, Vineet; Burda, Yura arXiv https://doi.org/10.48550/arXiv.2305.20050	preprint	January 2023
Voyager: An Open-Ended Embodied Agent with Large Language Models Wang, Guanzhi; Xie, Yuqi; Jiang, Yunfan arXiv https://doi.org/10.48550/arXiv.2305.16291	preprint	January 2023
Arbitrary lattice symmetries via block copolymer nanomeshes Majewski, Pawel W.; Rahman, Atikur; Black, Charles T. Nature Communications, Vol. 6, Issue 1 https://doi.org/10.1038/ncomms8448	journal	June 2015
Layout-aware text extraction from full-text PDF of scientific articles Ramakrishnan, Cartic; Patnia, Abhishek; Hovy, Eduard Source Code for Biology and Medicine, Vol. 7, Issue 1 https://doi.org/10.1186/1751-0473-7-7	journal	May 2012
Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling Xu, Weijia; Banburski-Fahey, Andrzej; Jojic, Nebojsa arXiv https://doi.org/10.48550/arXiv.2305.09993	preprint	January 2023
Matplotlib: A 2D Graphics Environment Hunter, John D. Computing in Science & Engineering, Vol. 9, Issue 3 https://doi.org/10.1109/MCSE.2007.55	journal	January 2007
A survey of machine learning for big data processing Qiu, Junfei; Wu, Qihui; Ding, Guoru EURASIP Journal on Advances in Signal Processing, Vol. 2016, Issue 1 https://doi.org/10.1186/s13634-016-0355-x	journal	May 2016
The Creativity of Text-to-Image Generation Oppenlaender, Jonas Proceedings of the 25th International Academic Mindtrek Conference https://doi.org/10.1145/3569219.3569352	conference	November 2022
Photomechanical Effects in Azo-Polymers Studied by Neutron Reflectometry Yager, Kevin G.; Tanchak, Oleh M.; Godbout, Chris Macromolecules, Vol. 39, Issue 26 https://doi.org/10.1021/ma0617320	journal	December 2006
PAL: Program-aided Language Models Gao, Luyu; Madaan, Aman; Zhou, Shuyan arXiv https://doi.org/10.48550/arXiv.2211.10435	preprint	January 2022
Python for Scientific Computing Oliphant, Travis E. Computing in Science & Engineering, Vol. 9, Issue 3 https://doi.org/10.1109/MCSE.2007.58	journal	January 2007
Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models Hsieh, Cheng-Yu; Chen, Si-An; Li, Chun-Liang arXiv https://doi.org/10.48550/arXiv.2308.00675	preprint	January 2023
Selective directed self-assembly of coexisting morphologies using block copolymer blends Stein, A.; Wright, G.; Yager, K. G. Nature Communications, Vol. 7, Issue 1 https://doi.org/10.1038/ncomms12366	journal	August 2016
Autonomous x-ray scattering Yager, Kevin G.; Majewski, Pawel W.; Noack, Marcus M. Nanotechnology, Vol. 34, Issue 32 https://doi.org/10.1088/1361-6528/acd25a	journal	May 2023

Similar Records

Large Language Models (LLMs) for Energy Systems Research

Conference · Fri Nov 10 00:00:00 EST 2023 · OSTI ID:2202517

Buster, Grant

Natural Language Processing for Text Based Event Extraction: Identifying Events of Interest Related to Worldwide State-Sponsored Civil Nuclear Power

Technical Report · Wed Mar 01 00:00:00 EST 2023 · OSTI ID:2202517

Danielson, Thomas L.; Deschaine, Larry M.

An asynchronous traversal engine for graph-based rich metadata management

Journal Article · Thu Jun 23 00:00:00 EDT 2016 · Parallel Computing · OSTI ID:2202517

Dai, Dong; Carns, Philip; Ross, Robert B.; +3 more

Related Subjects

77 NANOSCIENCE AND NANOTECHNOLOGY

Title: Domain-specific chatbots for science using embeddings

Citation Formats

References (63)

Similar Records

Related Subjects