Fetching the paper…

Reading the bibliography…

2024

Quantum Many-Body Physics Calculations with Large Language Models

Pan, Haining, Mudur, Nayantara, Taranto, Will et al.

Original
PDF
Post on X

Understand

Large language models (LLMs) have demonstrated an unprecedented ability to perform complex tasks in multiple domains, including mathematical and scientific reasoning.

We demonstrate that with carefully designed prompts, LLMs can accurately carry out key calculations in research papers in theoretical physics.
We focus on a broadly used approximation method in quantum physics: the Hartree-Fock method, requiring an analytic multi-step calculation deriving approximate Hamiltonian and corresponding self-consistency equations.
To carry out the calculations using LLMs, we design multi-step prompt templates that break down the analytic calculation into standardized steps with placeholders for problem-specific information.

Quantum Many-Body Physics Calculations with Large Language Models · Around

Built on

Condensed matter field theory (Cambridge university press, 2010)
Altland, A. & Simons, B. D · 2010
Earlier work this paper cites.
Outrageously large neural networks: The sparsely-gated mixture-of-experts layer
Original
Shazeer, N. et al · 2017
Earlier work this paper cites.
Language models are few-shot learners
Brown, T. et al · 2020
Earlier work this paper cites.
Scaling laws for neural language models
Original
Kaplan, J. et al · 2020
Earlier work this paper cites.
Measuring massive multitask language understanding
Original
Hendrycks, D. et al · 2020
Earlier work this paper cites.
Evaluating large language models trained on code
Original
Chen, M. et al · 2021
Earlier work this paper cites.
Measuring mathematical problem solving with the math dataset
Original
Hendrycks, D. et al · 2021
Earlier work this paper cites.
Training verifiers to solve math word problems
Original
Cobbe, K. et al · 2021
Earlier work this paper cites.
Competing magnetic states in transition metal dichalcogenide moir\’e materials
Hu, N. C. & MacDonald, A. H · 2021
Earlier work this paper cites.
Solving quantitative reasoning problems with language models
Lewkowycz, A. et al · 2022
Earlier work this paper cites.
Training compute-optimal large language models
Original
Hoffmann, J. et al · 2022
Earlier work this paper cites.
Galactica: A large language model for science
Original
Taylor, R. et al · 2022
Earlier work this paper cites.

Similar

Topological phases in ab-stacked mote 2 / wse 2 {\mathrm{mote}}_{2}/{\mathrm{wse}}_{2} : 𝕫 2 {\mathbb{z}}_{2} topological insulators, chern insulators, and topological charge density waves
Pan, H., Xie, M., Wu, F. & Das Sarma, S · 2022
Cited alongside, same era.
Palm 2 technical report
Original
Anil, R. et al · 2023
Cited alongside, same era.
Llama 2: Open foundation and fine-tuned chat models
Original
Touvron, H. et al · 2023
Cited alongside, same era.
Beyond the imitation game: Quantifying and extrapolating the capabilities of language models
Aarohi, S. e. a · 2023
Cited alongside, same era.
Examining the potential and pitfalls of chatgpt in science and engineering problem-solving
Original

Then

Gemini: a family of highly capable multimodal models
Original
Team, G. et al · 2023
Later among the works it cites.
Gpt-4 passes the bar exam
Katz, D. M., Bommarito, M. J., Gao, S. & Arredondo, P · 2023
Later among the works it cites.
The impact of large language models on scientific discovery: a preliminary study using gpt-4
Original
AI4Science, M. R. & Quantum, M. A · 2023
Later among the works it cites.
Paperqa: Retrieval-augmented generative agent for scientific research
Original
Lála, J. et al · 2023
Later among the works it cites.
Do large language models understand chemistry? a conversation with chatgpt
Castro Nascimento, C. M. & Pimentel, A. S · 2023
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Wang, K. D., Burkholder, E., Wieman, C., Salehi, S. & Haber, N · 2023

Cited alongside, same era.

Ai-assisted coding: Experiments with gpt-4

Original

Poldrack, R. A., Lu, T. & Beguš, G · 2023

Cited alongside, same era.

Large language models encode clinical knowledge

Singhal, K., Azizi, S., Tu, T. et al · 2023

Cited alongside, same era.

Capabilities of gpt-4 on medical challenge problems

Nori, H., King, N., McKinney, S. M., Carignan, D. & Horvitz, E · 2023

Cited alongside, same era.

Emergent autonomous scientific research capabilities of large language models

Boiko, D. A., MacKnight, R. & Gomes, G · 2023

Cited alongside, same era.

Mathematical discoveries from program search with large language models

Romera-Paredes, B. et al · 2023

Cited alongside, same era.

Gpt-4 technical report

Achiam, J. et al · 2023

Cited alongside, same era.

We focus solely on LLMs available via model APIs and not on LLMs and foundational models trained or tuned on domain specific data

Cited in the paper.

Assessment of chemistry knowledge in large language models that generate code

White, A. D. et al · 2023

Later among the works it cites.

Chemcrow: Augmenting large-language models with chemistry tools

Original

Bran, A. M., Cox, S., White, A. D. & Schwaller, P · 2023

Later among the works it cites.

Chameleon: Plug-and-play compositional reasoning with large language models

Lu, P. et al · 2023

Later among the works it cites.

Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface

Shen, Y. et al · 2023

Later among the works it cites.

LMSys Chatbot Arena Leaderboard

Hugging Face · 2024

Closest in time.

Solving olympiad geometry without human demonstrations

Trinh, T. H., Wu, Y., Le, Q. V., He, H. & Luong, T · 2024

Closest in time.