SimLM: Can Language Models Infer Parameters of Physical Systems?

• URL: http://arxiv.org/abs/2312.14215v2
• Date: Tue, 6 Feb 2024 10:15:01 GMT
• Title: SimLM: Can Language Models Infer Parameters of Physical Systems?
• Authors: Sean Memery, Mirella Lapata, Kartic Subr
• Abstract summary: We investigate the performance of Large Language Models (LLMs) at performing parameter inference in the context of physical systems. Our experiments suggest that they are not inherently suited to this task, even for simple systems. We propose a promising direction of exploration, which involves the use of physical simulators to augment the context of LLMs.
• Score: 56.38608628187024
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Several machine learning methods aim to learn or reason about complex physical systems. A common first-step towards reasoning is to infer system parameters from observations of its behavior. In this paper, we investigate the performance of Large Language Models (LLMs) at performing parameter inference in the context of physical systems. Our experiments suggest that they are not inherently suited to this task, even for simple systems. We propose a promising direction of exploration, which involves the use of physical simulators to augment the context of LLMs. We assess and compare the performance of different LLMs on a simple example with and without access to physical simulation.

Related papers

• LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models [35.01842161084472]
  We propose a new physical reasoning task and a dataset, dubbed TraySim. Our task involves predicting the dynamics of several objects on a tray that is given an external impact. We present LLMPhy, a zero-shot black-box optimization framework that leverages the physics knowledge and program synthesis abilities of LLMs. Our results show that the combination of the LLM and the physics engine leads to state-of-the-art zero-shot physical reasoning performance.
  arXiv  Detail & Related papers  (2024-11-12T18:56:58Z)
• Embed and Emulate: Contrastive representations for simulation-based inference [11.543221890134399]
  This paper introduces Embed and Emulate (E&E), a new simulation-based inference ( SBI) method based on contrastive learning. E&E learns a low-dimensional latent embedding of the data and a corresponding fast emulator in the latent space. We demonstrate superior performance over existing methods in a realistic, non-identifiable parameter estimation task.
  arXiv  Detail & Related papers  (2024-09-27T02:37:01Z)
• Verbalized Machine Learning: Revisiting Machine Learning with Language Models [63.10391314749408]
  We introduce the framework of verbalized machine learning (VML) VML constrains the parameter space to be human-interpretable natural language. We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.
  arXiv  Detail & Related papers  (2024-06-06T17:59:56Z)
• HARGPT: Are LLMs Zero-Shot Human Activity Recognizers? [9.414529772034985]
  We show that Large Language Models (LLMs) can comprehend raw IMU data and perform human activity recognition tasks in a zero-shot manner. We benchmark HARGPT on GPT4 using two public datasets of different inter-class similarities and compare various baselines both based on traditional machine learning and state-of-the-art deep classification models. Remarkably, LLMs successfully recognize human activities from raw IMU data and consistently outperform all the baselines on both datasets.
  arXiv  Detail & Related papers  (2024-03-05T07:34:51Z)
• Interpretable Meta-Learning of Physical Systems [4.343110120255532]
  Recent meta-learning methods rely on black-box neural networks, resulting in high computational costs and limited interpretability. We argue that multi-environment generalization can be achieved using a simpler learning model, with an affine structure with respect to the learning task. We demonstrate the competitive generalization performance and the low computational cost of our method by comparing it to state-of-the-art algorithms on physical systems.
  arXiv  Detail & Related papers  (2023-12-01T10:18:50Z)
• Explaining Emergent In-Context Learning as Kernel Regression [61.57151500616111]
  Large language models (LLMs) have initiated a paradigm shift in transfer learning. In this paper, we investigate the reason why a transformer-based language model can accomplish in-context learning after pre-training. We find that during ICL, the attention and hidden features in LLMs match the behaviors of a kernel regression.
  arXiv  Detail & Related papers  (2023-05-22T06:45:02Z)
• Which priors matter? Benchmarking models for learning latent dynamics [70.88999063639146]
  Several methods have proposed to integrate priors from classical mechanics into machine learning models. We take a sober look at the current capabilities of these models. We find that the use of continuous and time-reversible dynamics benefits models of all classes.
  arXiv  Detail & Related papers  (2021-11-09T23:48:21Z)
• An Extensible Benchmark Suite for Learning to Simulate Physical Systems [60.249111272844374]
  We introduce a set of benchmark problems to take a step towards unified benchmarks and evaluation protocols. We propose four representative physical systems, as well as a collection of both widely used classical time-based and representative data-driven methods.
  arXiv  Detail & Related papers  (2021-08-09T17:39:09Z)
• Learning to Simulate Complex Physics with Graph Networks [68.43901833812448]
  We present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains. Our framework---which we term "Graph Network-based Simulators" (GNS)--represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time.
  arXiv  Detail & Related papers  (2020-02-21T16:44:28Z)
• Operationally meaningful representations of physical systems in neural networks [4.192302677744796]
  We present a neural network architecture based on the notion that agents dealing with different aspects of a physical system should be able to communicate relevant information as efficiently as possible to one another. This produces representations that separate different parameters which are useful for making statements about the physical system in different experimental settings.
  arXiv  Detail & Related papers  (2020-01-02T19:01:31Z)

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.