PKG-DPO: Optimizing Domain-Specific AI systems with Physics Knowledge Graphs and Direct Preference Optimization

• URL: http://arxiv.org/abs/2508.18391v1
• Date: Mon, 25 Aug 2025 18:31:03 GMT
• Title: PKG-DPO: Optimizing Domain-Specific AI systems with Physics Knowledge Graphs and Direct Preference Optimization
• Authors: Nitin Nagesh Kulkarni, Bryson Wilcox, Max Sawa, Jason Thom,
• Abstract summary: We introduce PKG-DPO, a novel framework that integrates Physics Knowledge Graphs (PKGs) with Direct Preference Optimization (DPO)<n>PKG-DPO 17% achieves fewer constraint violations and an 11% higher Physics Score compared to KG-DPO (knowledge graph-based DPO)<n>While our primary focus is on metal joining, the framework is broadly applicable to other multi-scale, physics-driven domains.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Advancing AI systems in scientific domains like physics, materials science, and engineering calls for reasoning over complex, multi-physics phenomena while respecting governing principles. Although Large Language Models (LLMs) and existing preference optimization techniques perform well on standard benchmarks, they often struggle to differentiate between physically valid and invalid reasoning. This shortcoming becomes critical in high-stakes applications like metal joining, where seemingly plausible yet physically incorrect recommendations can lead to defects, material waste, equipment damage, and serious safety risks. To address this challenge, we introduce PKG-DPO, a novel framework that integrates Physics Knowledge Graphs (PKGs) with Direct Preference Optimization (DPO) to enforce physical validity in AI-generated outputs. PKG-DPO comprises three key components A) hierarchical physics knowledge graph that encodes cross-domain relationships, conservation laws, and thermodynamic principles. B) A physics reasoning engine that leverages structured knowledge to improve discrimination between physically consistent and inconsistent responses. C) A physics-grounded evaluation suite designed to assess compliance with domain-specific constraints. PKG-DPO achieves 17% fewer constraint violations and an 11% higher Physics Score compared to KG-DPO (knowledge graph-based DPO). Additionally, PKG-DPO demonstrates a 12\% higher relevant parameter accuracy and a 7% higher quality alignment in reasoning accuracy. While our primary focus is on metal joining, the framework is broadly applicable to other multi-scale, physics-driven domains, offering a principled approach to embedding scientific constraints into preference learning.

Related papers

• Learning Data-Efficient and Generalizable Neural Operators via Fundamental Physics Knowledge [8.269904705399474]
  Recent advances in machine learning have enabled neural operators to serve as powerful surrogates for modeling the evolution of physical systems.<n>We propose a multiphysics training framework that jointly learns from both the original PDEs and their simplified basic forms.<n>Our framework enhances data efficiency, reduces predictive errors, and improves out-of-distribution (OOD) generalization.
  arXiv  Detail & Related papers  (2026-02-16T20:45:10Z)
• SciIF: Benchmarking Scientific Instruction Following Towards Rigorous Scientific Intelligence [60.202862987441684]
  We introduce scientific instruction following: the capability to solve problems while strictly adhering to the constraints that establish scientific validity.<n>Specifically, we introduce SciIF, a multi-discipline benchmark that evaluates this capability by pairing university-level problems with a fixed catalog of constraints.<n>By measuring both solution correctness and multi-constraint adherence, SciIF enables finegrained diagnosis of compositional reasoning failures.
  arXiv  Detail & Related papers  (2026-01-08T09:45:58Z)
• PI-MFM: Physics-informed multimodal foundation model for solving partial differential equations [6.876642270107136]
  We propose a physics-informed multimodal foundation model (PI-MFM) framework that directly enforces governing equations during pretraining and adaptation.<n>PI-MFM takes symbolic representations of PDEs as the input, and automatically assembles PDE residual losses from the input expression.<n>On a benchmark of 13 parametric one-dimensional time-dependent PDE families, PI-MFM consistently outperforms purely data-driven counterparts.
  arXiv  Detail & Related papers  (2025-12-28T19:43:57Z)
• Hard-Constrained Neural Networks with Physics-Embedded Architecture for Residual Dynamics Learning and Invariant Enforcement in Cyber-Physical Systems [0.5735035463793009]
  We formalize the Hybrid Recurrent Physics-Informed Neural Network (HRPINN), a general-purpose architecture that embeds known physics as a hard structural constraint within a recurrent integrator to learn only residual dynamics.<n>Second, we introduce the Projected HRPINN (PHRPINN), a novel extension that integrates a predict-project mechanism to strictly enforce algebraic invariants by design.<n>We validate HRPINN on a real-world battery prognostics DAE and evaluate PHRPINN on a suite of standard constrained benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T16:06:24Z)
• PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning [57.868248683256574]
  PRISM-Physics is a process-level evaluation framework and benchmark for complex physics reasoning problems.<n> Solutions are represented as directed acyclic graphs (DAGs) of formulas.<n>Results show that our evaluation framework is aligned with human experts' scoring.
  arXiv  Detail & Related papers  (2025-10-03T17:09:03Z)
• CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics [71.42168240638462]
  CMPhysBench is designed to assess the proficiency of Large Language Models in Condensed Matter Physics.<n>Our results show that even the best models, Grok-4, reach only 36 average SEED score and 28% accuracy on CMPhysBench.
  arXiv  Detail & Related papers  (2025-08-25T15:32:22Z)
• Causal-Aware Intelligent QoE Optimization for VR Interaction with Adaptive Keyframe Extraction [6.2819120598047]
  This paper proposes an intelligent framework to maximize quality of experience (QoE) in VR games.<n>It integrates adaptive extraction with causal-aware reinforcement learning (RL)<n> Experiments show that our framework significantly reduces interactive latency, enhances QoE, and maintains fairness.
  arXiv  Detail & Related papers  (2025-06-24T07:32:34Z)
• Flow Matching Meets PDEs: A Unified Framework for Physics-Constrained Generation [21.321570407292263]
  We propose Physics-Based Flow Matching, a generative framework that embeds physical constraints, both PDE residuals and algebraic relations, into the flow matching objective.<n>We show that our approach yields up to an $8times$ more accurate physical residuals compared to FM, while clearly outperforming existing algorithms in terms of distributional accuracy.
  arXiv  Detail & Related papers  (2025-06-10T09:13:37Z)
• Paving the way for scientific foundation models: enhancing generalization and robustness in PDEs with constraint-aware pre-training [49.8035317670223]
  A scientific foundation model (SciFM) is emerging as a promising tool for learning transferable representations across diverse domains.<n>We propose incorporating PDE residuals into pre-training either as the sole learning signal or in combination with data loss to compensate for limited or infeasible training data.<n>Our results show that pre-training with PDE constraints significantly enhances generalization, outperforming models trained solely on solution data.
  arXiv  Detail & Related papers  (2025-03-24T19:12:39Z)
• Advancing Generalization in PINNs through Latent-Space Representations [71.86401914779019]
  Physics-informed neural networks (PINNs) have made significant strides in modeling dynamical systems governed by partial differential equations (PDEs)<n>We propose PIDO, a novel physics-informed neural PDE solver designed to generalize effectively across diverse PDE configurations.<n>We validate PIDO on a range of benchmarks, including 1D combined equations and 2D Navier-Stokes equations.
  arXiv  Detail & Related papers  (2024-11-28T13:16:20Z)
• Direct Preference Optimization for Primitive-Enabled Hierarchical Reinforcement Learning [75.9729413703531]
  DIPPER is a novel HRL framework that formulates hierarchical policy learning as a bi-level optimization problem.<n>We show that DIPPER achieves up to 40% improvement over state-of-the-art baselines in sparse reward scenarios.
  arXiv  Detail & Related papers  (2024-11-01T04:58:40Z)
• Secrets of RLHF in Large Language Models Part I: PPO [81.01936993929127]
  Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. In this report, we dissect the framework of RLHF, re-evaluate the inner workings of PPO, and explore how the parts comprising PPO algorithms impact policy agent training.
  arXiv  Detail & Related papers  (2023-07-11T01:55:24Z)
• Physics-aware deep learning framework for linear elasticity [0.0]
  The paper presents an efficient and robust data-driven deep learning (DL) computational framework for linear continuum elasticity problems. For an accurate representation of the field variables, a multi-objective loss function is proposed. Several benchmark problems including the Airimaty solution to elasticity and the Kirchhoff-Love plate problem are solved.
  arXiv  Detail & Related papers  (2023-02-19T20:33:32Z)
• PID-GAN: A GAN Framework based on a Physics-informed Discriminator for Uncertainty Quantification with Physics [2.4309139330334846]
  In scientific applications, it is important to inform the learning of deep learning models with knowledge of physics to produce physically consistent and generalized solutions. We propose a novel physics-informed GAN architecture, termed PID-GAN, where the knowledge of physics is used to inform the learning of both the generator and discriminator models. We show that our proposed PID-GAN framework does not suffer from imbalance of generator gradients from multiple loss terms as compared to state-of-the-art.
  arXiv  Detail & Related papers  (2021-06-06T00:12:57Z)
• A hybrid MGA-MSGD ANN training approach for approximate solution of linear elliptic PDEs [0.0]
  We introduce a hybrid "Modified Genetic-Multilevel Gradient Descent" (MGA-MSGD) training algorithm. It considerably improves accuracy and efficiency of solving 3D mechanical problems described, in strong-form, by PDEs via ANNs.
  arXiv  Detail & Related papers  (2020-12-18T10:59:07Z)
• Benchmarking adaptive variational quantum eigensolvers [63.277656713454284]
  We benchmark the accuracy of VQE and ADAPT-VQE to calculate the electronic ground states and potential energy curves. We find both methods provide good estimates of the energy and ground state. gradient-based optimization is more economical and delivers superior performance than analogous simulations carried out with gradient-frees.
  arXiv  Detail & Related papers  (2020-11-02T19:52:04Z)

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.