Quantum many-body physics calculations with large language models
Abstract Large language models (LLMs) have demonstrated abilities 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 physi...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Communications Physics |
| Online Access: | https://doi.org/10.1038/s42005-025-01956-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571613365665792 |
|---|---|
| author | Haining Pan Nayantara Mudur William Taranto Maria Tikhanovskaya Subhashini Venugopalan Yasaman Bahri Michael P. Brenner Eun-Ah Kim |
| author_facet | Haining Pan Nayantara Mudur William Taranto Maria Tikhanovskaya Subhashini Venugopalan Yasaman Bahri Michael P. Brenner Eun-Ah Kim |
| author_sort | Haining Pan |
| collection | DOAJ |
| description | Abstract Large language models (LLMs) have demonstrated abilities 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. We evaluate GPT-4’s performance in executing the calculation for 15 papers from the past decade, demonstrating that, with the correction of intermediate steps, it can correctly derive the final Hartree-Fock Hamiltonian in 13 cases. Aggregating across all research papers, we find an average score of 87.5 (out of 100) on the execution of individual calculation steps. We further use LLMs to mitigate the two primary bottlenecks in this evaluation process: (i) extracting information from papers to fill in templates and (ii) automatic scoring of the calculation steps, demonstrating good results in both cases. |
| format | Article |
| id | doaj-art-c07cad183126418c9bf6406bb073ad46 |
| institution | Kabale University |
| issn | 2399-3650 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Communications Physics |
| spelling | doaj-art-c07cad183126418c9bf6406bb073ad462025-02-02T12:28:05ZengNature PortfolioCommunications Physics2399-36502025-01-01811810.1038/s42005-025-01956-yQuantum many-body physics calculations with large language modelsHaining Pan0Nayantara Mudur1William Taranto2Maria Tikhanovskaya3Subhashini Venugopalan4Yasaman Bahri5Michael P. Brenner6Eun-Ah Kim7Department of Physics, Cornell UniversityGoogle ResearchDepartment of Physics, Cornell UniversityGoogle ResearchGoogle ResearchGoogle DeepMindGoogle ResearchDepartment of Physics, Cornell UniversityAbstract Large language models (LLMs) have demonstrated abilities 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. We evaluate GPT-4’s performance in executing the calculation for 15 papers from the past decade, demonstrating that, with the correction of intermediate steps, it can correctly derive the final Hartree-Fock Hamiltonian in 13 cases. Aggregating across all research papers, we find an average score of 87.5 (out of 100) on the execution of individual calculation steps. We further use LLMs to mitigate the two primary bottlenecks in this evaluation process: (i) extracting information from papers to fill in templates and (ii) automatic scoring of the calculation steps, demonstrating good results in both cases.https://doi.org/10.1038/s42005-025-01956-y |
| spellingShingle | Haining Pan Nayantara Mudur William Taranto Maria Tikhanovskaya Subhashini Venugopalan Yasaman Bahri Michael P. Brenner Eun-Ah Kim Quantum many-body physics calculations with large language models Communications Physics |
| title | Quantum many-body physics calculations with large language models |
| title_full | Quantum many-body physics calculations with large language models |
| title_fullStr | Quantum many-body physics calculations with large language models |
| title_full_unstemmed | Quantum many-body physics calculations with large language models |
| title_short | Quantum many-body physics calculations with large language models |
| title_sort | quantum many body physics calculations with large language models |
| url | https://doi.org/10.1038/s42005-025-01956-y |
| work_keys_str_mv | AT hainingpan quantummanybodyphysicscalculationswithlargelanguagemodels AT nayantaramudur quantummanybodyphysicscalculationswithlargelanguagemodels AT williamtaranto quantummanybodyphysicscalculationswithlargelanguagemodels AT mariatikhanovskaya quantummanybodyphysicscalculationswithlargelanguagemodels AT subhashinivenugopalan quantummanybodyphysicscalculationswithlargelanguagemodels AT yasamanbahri quantummanybodyphysicscalculationswithlargelanguagemodels AT michaelpbrenner quantummanybodyphysicscalculationswithlargelanguagemodels AT eunahkim quantummanybodyphysicscalculationswithlargelanguagemodels |