LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
- URL: http://arxiv.org/abs/2405.09783v1
- Date: Thu, 16 May 2024 03:04:10 GMT
- Title: LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery
- Authors: Pingchuan Ma, Tsun-Hsuan Wang, Minghao Guo, Zhiqing Sun, Joshua B. Tenenbaum, Daniela Rus, Chuang Gan, Wojciech Matusik,
- Abstract summary: We propose to enhance the knowledge-driven, abstract reasoning abilities of Large Language Models with the computational strength of simulations.
We introduce Scientific Generative Agent (SGA), a bilevel optimization framework.
We conduct experiments to demonstrate our framework's efficacy in law discovery and molecular design.
- Score: 141.39722070734737
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models have recently gained significant attention in scientific discovery for their extensive knowledge and advanced reasoning capabilities. However, they encounter challenges in effectively simulating observational feedback and grounding it with language to propel advancements in physical scientific discovery. Conversely, human scientists undertake scientific discovery by formulating hypotheses, conducting experiments, and revising theories through observational analysis. Inspired by this, we propose to enhance the knowledge-driven, abstract reasoning abilities of LLMs with the computational strength of simulations. We introduce Scientific Generative Agent (SGA), a bilevel optimization framework: LLMs act as knowledgeable and versatile thinkers, proposing scientific hypotheses and reason about discrete components, such as physics equations or molecule structures; meanwhile, simulations function as experimental platforms, providing observational feedback and optimizing via differentiability for continuous parts, such as physical parameters. We conduct extensive experiments to demonstrate our framework's efficacy in constitutive law discovery and molecular design, unveiling novel solutions that differ from conventional human expectations yet remain coherent upon analysis.
Related papers
- Scientific Language Modeling: A Quantitative Review of Large Language
Models in Molecular Science [27.874571056109758]
Large language models (LLMs) offer a fresh approach to tackle scientific problems from a natural language processing (NLP) perspective.
We propose a multi-modal benchmark, named ChEBI-20-MM, and perform 1263 experiments to assess the model's compatibility with data modalities and knowledge acquisition.
Our pioneering analysis offers an exploration of the learning mechanism and paves the way for advancing SLM in molecular science.
arXiv Detail & Related papers (2024-02-06T16:12:36Z) - Scientific Large Language Models: A Survey on Biological & Chemical Domains [47.97810890521825]
Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension.
The application of LLMs extends beyond conventional linguistic boundaries, encompassing specialized linguistic systems developed within various scientific disciplines.
As a burgeoning area in the community of AI for Science, scientific LLMs warrant comprehensive exploration.
arXiv Detail & Related papers (2024-01-26T05:33:34Z) - SciGLM: Training Scientific Language Models with Self-Reflective
Instruction Annotation and Tuning [60.14510984576027]
SciGLM is a suite of scientific language models able to conduct college-level scientific reasoning.
We apply a self-reflective instruction annotation framework to generate step-by-step reasoning for unlabelled scientific questions.
We fine-tuned the ChatGLM family of language models with SciInstruct, enhancing their scientific and mathematical reasoning capabilities.
arXiv Detail & Related papers (2024-01-15T20:22:21Z) - Large Language Models are Zero Shot Hypothesis Proposers [17.612235393984744]
Large Language Models (LLMs) hold a wealth of global and interdisciplinary knowledge that promises to break down information barriers.
We construct a dataset consist of background knowledge and hypothesis pairs from biomedical literature.
We evaluate the hypothesis generation capabilities of various top-tier instructed models in zero-shot, few-shot, and fine-tuning settings.
arXiv Detail & Related papers (2023-11-10T10:03:49Z) - Large Language Models for Automated Open-domain Scientific Hypotheses Discovery [50.40483334131271]
This work proposes the first dataset for social science academic hypotheses discovery.
Unlike previous settings, the new dataset requires (1) using open-domain data (raw web corpus) as observations; and (2) proposing hypotheses even new to humanity.
A multi- module framework is developed for the task, including three different feedback mechanisms to boost performance.
arXiv Detail & Related papers (2023-09-06T05:19:41Z) - Machine learning enabled experimental design and parameter estimation
for ultrafast spin dynamics [54.172707311728885]
We introduce a methodology that combines machine learning with Bayesian optimal experimental design (BOED)
Our method employs a neural network model for large-scale spin dynamics simulations for precise distribution and utility calculations in BOED.
Our numerical benchmarks demonstrate the superior performance of our method in guiding XPFS experiments, predicting model parameters, and yielding more informative measurements within limited experimental time.
arXiv Detail & Related papers (2023-06-03T06:19:20Z) - Simulation Intelligence: Towards a New Generation of Scientific Methods [81.75565391122751]
"Nine Motifs of Simulation Intelligence" is a roadmap for the development and integration of the essential algorithms necessary for a merger of scientific computing, scientific simulation, and artificial intelligence.
We argue the motifs of simulation intelligence are interconnected and interdependent, much like the components within the layers of an operating system.
We believe coordinated efforts between motifs offers immense opportunity to accelerate scientific discovery.
arXiv Detail & Related papers (2021-12-06T18:45:31Z) - Interpretable and Explainable Machine Learning for Materials Science and
Chemistry [2.2175470459999636]
We summarize applications of interpretability and explainability techniques for materials science and chemistry.
We discuss various challenges for interpretable machine learning in materials science and, more broadly, in scientific settings.
We showcase a number of exciting developments in other fields that could benefit interpretability in material science and chemistry problems.
arXiv Detail & Related papers (2021-11-01T15:40:36Z) - Scientific intuition inspired by machine learning generated hypotheses [2.294014185517203]
We shift the focus on the insights and the knowledge obtained by the machine learning models themselves.
We apply gradient boosting in decision trees to extract human interpretable insights from big data sets from chemistry and physics.
The ability to go beyond numerics opens the door to use machine learning to accelerate the discovery of conceptual understanding.
arXiv Detail & Related papers (2020-10-27T12:12:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.