Search NASA⌕ Search

SEARCH · Search NASA

Results for “Language model”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 325 records · Page 18

Transformer quantum state: A multipurpose model for quantum many-body problems

Here, inspired by the advancements in large language models based on transformers, we introduce the transformer quantum state (TQS): a versatile machine learning model for quantum many-body problems. In sharp contrast to Hamiltonian/task specific models, TQS can generate the entire phase diagram, predict field strengths with experimental measurements, and transfer such a knowledge to new systems it has never been trained on before, all within a single model. With specific tasks, fine-tuning the TQS produces accurate results with small computational cost. Versatile by design, TQS can be easily adapted to new tasks, thereby pointing towards a general-purpose model for various challenging quantum problems.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

The IDAES process modeling framework and model library—Flexibility for process simulation and optimization

Abstract Energy systems and manufacturing processes of the 21st century are becoming increasingly dynamic and interconnected, which require new capabilities to effectively model and optimize their design and operations. Such next generation computational tools must leverage state‐of‐the‐art techniques in optimization and be able to rapidly incorporate new advances. To address these requirements, we have developed the Institute for the Design of Advanced Energy Systems (IDAES) Integrated Platform, which builds on the strengths of both process simulators (model libraries) and algebraic modeling languages (advanced solvers). This paper specifically presents the IDAES Core Modeling Framework (IDAES‐CMF), along with a case study demonstrating the application of the framework to solve process optimization problems. Capabilities provided by this framework include a flexible, modifiable, open‐source platform for optimization of process flowsheets utilizing state‐of‐the‐art solvers and solution techniques, fully open and extensible libraries of dynamic unit operations models and thermophysical property models, and integrated support for superstructure‐based conceptual design and optimization under uncertainty.

42 ENGINEERING↗

Modeling without categorical variables : a mixed-integer nonlinear program for the optimization of thermal insulation systems.

Optimal design applications are often modeled by using categorical variables to express discrete design decisions, such as material types. A disadvantage of using categorical variables is the lack of continuous relaxations, which precludes the use of modern integer programming techniques. We show how to express categorical variables with standard integer modeling techniques, and we illustrate this approach on a load-bearing thermal insulation system. The system consists of a number of insulators of different materials and intercepts that minimize the heat flow from a hot surface to a cold surface. Our new model allows us to employ black-box modeling languages and solvers and illustrates the interplay between integer and nonlinear modeling techniques. We present numerical experience that illustrates the advantage of the standard integer model.

97 MATHEMATICS AND COMPUTING↗

BuildingQA: A Benchmark for Natural Language Question Answering over Building Knowledge Graphs

Graph-based representations of building metadata using ontologies like Brick are vital for smart building applications, but querying them remains a challenge for practitioners. Knowledge Graph Question Answering (KGQA) systems, meant to retrieve answers from natural language questions, traditionally require large-scale training data, making them ill-suited for the specialized and data-scarce building domain. The advent of Large Language Models (LLMs) offers a paradigm shift, enabling zero-shot natural language querying without building/domain-specific training. Yet, there is no standardized benchmark for building-specific KGQA which can guide and validate research in this area. To address this gap, our work makes three primary contributions. First, we introduce the BuildingQA Benchmark Dataset, constructed through a multi-stage process of collecting practitioner data, augmenting it with LLMs for linguistic diversity, and curating a final set of 188 questions across 4 buildings. Second, we characterize the benchmark's complexity and ambiguity, introducing a novel method to quantify its "lexical gap" and providing a four-stage diagnostic framework for analyzing how systems fail. Third, we benchmark zero-shot LLM-powered KGQA systems to establish baseline performance and analyze their failure modes. Our evaluation reveals that top-performing systems achieve a maximum F1 score of only 0.38. This result does not indicate a failure of these powerful systems, but rather underscores the unique challenges posed by our benchmark. It demonstrates a critical performance gap, showing that current methods successful on general KGs struggle with the specific lexical and structural nuances of the building domain. BuildingQA1 thus provides the benchmark dataset and foundational analysis needed to drive the development of novel, domain-aware methods required to unlock the use of semantic data in buildings.

Mulayim, Ozan Baris↗

HALLUFIELD: DETECTING LLM HALLUCINATIONS VIA FIELD-THEORETIC MODELING

A research-focused Python package that implements our hallucination-detection method for large language models(LLMs). The code computes stability signals from LLM predictions across various hyperparameters sweeps and combines free-energy/entropy–style metrics to flag likely hallucinations, with tunable thresholds for batch scoring. The repo includes evaluation scripts, config files, and example notebooks to reproduce benchmark results and ablations; it depends on standard open-source libraries (PyTorch, Hugging Face) and runs on CPU/GPU. The repository examples only use public models/datasets only.

Bhattarai, Manish [Los Alamos National Labs]↗

Trend Analysis in Biomedical Texts via Vector Space Model Synonym Extraction

Accurate synonym extraction is a highly desired tool in computational semantics and natural language processing (NLP). Intrinsic to many current language models is the Vector Space Model (VSM) whereby linguistic properties are modeled by real vectors of small length compared to the document size. Here, several vector models are discussed. Utilizing the open source Word2Vec tool, temporal trends in biomedical abstracts from MEDLINE have been analyzed via a unique transformation matrix method. Additionally, accuracy of the word vector method and clustering of temporal trends are discussed.

59 BASIC BIOLOGICAL SCIENCES↗

Review of Grey Box/Black Box Data Contamination Metrics on Open and Commercial Models

Dataset contamination is a problem where benchmarks and tasks used to evaluate the capabilities of Large Language Models (LLMs) have been incorporated into the training dataset of the models. This gives a false sense of performance that can overestimate how these models will function on truly unseen data. This problem becomes worse with commercial LLMs with larger and non-accessible training data, so techniques have been developed to try to measure the degree to which a model is contaminated with a benchmark’s data. To understand the effectiveness of these techniques, particularly when evaluating contamination on coding tasks, we review trends and categorize techniques by the degree of access to the model that is required. The research literature on this topic has reported mixed effectiveness of these techniques, so we select a set of black box (text access only) and grey box (access to model loss/probabilities required) techniques and apply them to both commercial and non-commercial models. We implement these metrics as part of a framework to test the contamination of Python code in LLMs to see to what extent we can replicate the effectiveness (or ineffectiveness) of these contamination detection techniques. Though we find mixed results in the capabilities of these metrics to identify contamination, we do observe evidence that they can identify contamination (broadly) in fine-tuned models when both a baseline and fine-tuned model is present. Additionally, similarity metrics were able to identify between contaminated and uncontaminated data even in situations where the data is distributionally similar (e.g., drawn from the same set of code projects).

97 MATHEMATICS AND COMPUTING↗

Targeting tissues via dynamic human systems modeling in generative design

Drug discovery is a complex, costly process with high failure rates. A successful drug should bind to a target, be deliverable to an intended site of activity, and promote a desired pharmacological effect without causing toxicity. Typically, these factors are evaluated in series over the course of a pipeline where the number of candidates is sequentially whittled down from a very large initial pool. One promise of AI-driven discovery is the opportunity to evaluate multiple facets of drug performance in parallel. However, despite ML-driven advancements, current models for pharmacological property prediction are exclusively trained to predict molecular properties, ignoring important, dynamic biodistribution and bioactivity effects. Here, we present our progress towards incorporating quantitative systems physiology models into an AI-enabled drug design and molecular generation pipeline. Within a genetic algorithm, we include human-relevant physiologically based pharmacokinetic (PBPK) models. These PBPK models leverage properties that are predicted by a fine-tuned molecular language model. Together, these models will aid in capturing the mapping between molecules and therapeutic outcomes that is necessary to accelerate the drug discovery process.

Fox, Zach↗

I Can’t Read All That! Improving the Usability of Semantic Models Using Concise, Ontology-Agnostic, Building-Specific Schemas

Semantic ontologies have enabled the creation of formalized, machine-readable descriptions of heterogenous building systems by providing dictionaries of well defined concepts that can be applied to model them. Within a semantic model of a particular building, a subset of an ontology's concepts may be applied in different ways to represent a particular perspective of the building's systems. How the concepts were applied can only be understood by examining the large amount of instance data within a semantic model, which leads to usability challenges. We propose a concise, ontology-agnostic method for defining building-specific schema (b-schema) graphs that summarize the structure and content of a semantic model. This approach provides a queryable and concise representation of the model's contents, separate from the instance data within a model, that can mitigate the challenges posed by the size and complexity of semantic models in processes such as visualization, querying, validation, and the use of large language models (LLMs). We validate our approach on semantic models based on the Brick and ASHRAE S223 ontologies. Results demonstrate that b-schemas significantly reduce the complexity of visual interpretation, accelerate SPARQL queries and SHACL validation, and improve LLM-based knowledge graph question answering.

Paul, Lazlo [Lawrence Berkeley National Laboratory↗

Economic Assessment of Nuclear Hybrid Energy Systems: Optimization using RAVEN

The energy market supply is under pressure to achieve competing goals, such as minimizing the cost of electricity and greenhouse gas emissions while achieving grid resilience and reliability and meeting regulatory requirements. To study different scenarios for possible evolutions of the energy market that assume a certain renewable penetration and the possible introduction of hybrid nuclear reactors, the HYBRID modeling and simulation project has been initiated by INL. The term hybrid nuclear reactor here refers to nuclear power plants that not only produce electricity, but can also sell heat to an industrial process, like a hydrogen generation or water desalination plant. The RAVEN (Risk Analysis Virtual Environment) code developed at INL together with the modeling language Modelica (the Dymola compiler is used) have been selected as the main modeling tools for the HYBRID modeling and simulation project. This summary outlines the challenge, presents an overview of the developments in the RAVEN code needed to solve it and shows an illustrative example calculation. The HYBRID modeling and simulation project is a multi laboratory effort, involving research teams from three different U.S. national laboratories, led by the Idaho National Laboratory (INL) and supported by the Argonne National Laboratory (ANL) and the Oak Ridge National Laboratory (ORNL)

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

AI Benchmark Democratization and Carpentry

Benchmarks are a cornerstone of modern machine learning, enabling reproducibility, comparison, and scientific progress. However, AI benchmarks are increasingly complex, requiring dynamic, AI-focused workflows. Rapid evolution in model architectures, scale, datasets, and deployment contexts makes evaluation a moving target. Large language models often memorize static benchmarks, causing a gap between benchmark results and real-world performance. Beyond traditional static benchmarks, continuous adaptive benchmarking frameworks are needed to align scientific assessment with deployment risks. This calls for skills and education in AI Benchmark Carpentry. From our experience with MLCommons, educational initiatives, and programs like the DOE's Trillion Parameter Consortium, key barriers include high resource demands, limited access to specialized hardware, lack of benchmark design expertise, and uncertainty in relating results to application domains. Current benchmarks often emphasize peak performance on top-tier hardware, offering limited guidance for diverse, real-world scenarios. Benchmarking must become dynamic, incorporating evolving models, updated data, and heterogeneous platforms while maintaining transparency, reproducibility, and interpretability. Democratization requires both technical innovation and systematic education across levels, building sustained expertise in benchmark design and use. Benchmarks should support application-relevant comparisons, enabling informed, context-sensitive decisions. Dynamic, inclusive benchmarking will ensure evaluation keeps pace with AI evolution and supports responsible, reproducible, and accessible AI deployment. Community efforts can provide a foundation for AI Benchmark Carpentry.

von Laszewski, Gregor [Virginia U.]↗

EnergyPlus-MCP: A model-context-protocol server for ai-driven building energy modeling

Traditional building energy modeling with the EnergyPlus building performance simulation engine requires domain expertise, programming skills, and intensive manual efforts limiting its effective adoption. This paper introduces EnergyPlus-MCP, the first open-source Model Context Protocol (MCP) server specifically designed for EnergyPlus simulation workflows, establishing a new foundational infrastructure for AI-driven building energy modeling. The MCP server implements a layered architecture with 35 specialized tools spanning model management, editing and analysis, HVAC and other systems configuration inspection, and simulation execution, enabling Large Language Models to interact with EnergyPlus through conversational interfaces. The server addresses critical workflow barriers by automating model validation, streamlining energy efficiency measures modification, and providing intelligent output management with interactive visualization. Through practical demonstrations using a multi-zone building retrofit analysis, we show how the EnergyPlus-MCP server significantly reduces manual efforts while maintaining full simulation rigor. By providing accessible natural language interfaces to sophisticated building energy analysis, this approach enables scalable deployment of simulation expertise across public and private organizations, educational institutions, and research teams, fundamentally transforming traditional building energy modeling practices.

AI↗

PAO 1.0: A Python Library for Adversarial Optimization

PAO is a Python-based package for Adversarial Optimization. The goal of this package is to provide a general modeling and analysis capability for bilevel, trilevel and other multilevel optimization forms that express adversarial dynamics. PAO integrates two different modeling abstractions: 1. Algebraic models extend the modeling concepts in the Pyomo algebraic modeling language to express problems with an intuitive algebraic syntax. Thus, we expect that this modeling abstraction will commonly be used by PAO end-users. 2. Compact models express objective and constraints in a manner that is typically used to express the mathematical form of these problems (e.g. using vector and matrix data types). PAO denes custom Multilevel Problem Representations (MPRs) that simplify the implementation of solvers for bilevel, trilevel and other multilevel optimization problems.

97 MATHEMATICS AND COMPUTING↗

Finch: Toxicity Dose Response Curve Prediction of Chemical Compounds and Mixtures

A paradigm shift in chemical risk assessment is emphasizing mixture testing over single compound analysis, eliminating animal testing, and adopting advanced modeling approaches to understand mixture activity profiles. However, existing computational models largely focus on single chemicals, with few effective solutions for modeling complex mixtures that account for synergistic or antagonistic effects and multiple Modes of Action (MoA). Conventional methods like concentration addition (CA) and independent action (IA) are insufficient for this task as they are designed for simplistic interactions and struggle to account for the dynamic and multifaceted nature of chemical mixtures, such as overlapping MoA and non-linear interactions. Finch offers a novel approach utilizing deep learning (DL) embeddings and multi-task quantitative structure-activity relationship (QSAR) models to improve chemical exposure prediction. By leveraging molecular descriptors, physiochemical properties, and large language model (LLM) embeddings from SMILES inputs, Finch preserves critical information in a latent space thereby enhancing predictive accuracy. The multi-task learning aspect of Finch is highly advantageous, as it simultaneously optimizes multiple loss functions, leveraging all available data across tasks to develop generalized representations that effectively capture complex ingredient interactions within mixtures.

59 BASIC BIOLOGICAL SCIENCES↗

Deep learning workflow for the inverse design of molecules with specific optoelectronic properties

The inverse design of novel molecules with a desirable optoelectronic property requires consideration of the vast chemical spaces associated with varying chemical composition and molecular size. First principles-based property predictions have become increasingly helpful for assisting the selection of promising candidate chemical species for subsequent experimental validation. However, a brute-force computational screening of the entire chemical space is decidedly impossible. To alleviate the computational burden and accelerate rational molecular design, we here present an iterative deep learning workflow that combines (i) the density-functional tight-binding method for dynamic generation of property training data, (ii) a graph convolutional neural network surrogate model for rapid and reliable predictions of chemical and physical properties, and (iii) a masked language model. As proof of principle, we employ our workflow in the iterative generation of novel molecules with a target energy gap between the highest occupied molecular orbital (HOMO) and the lowest unoccupied molecular orbital (LUMO).

97 MATHEMATICS AND COMPUTING↗

Visual Exploration of Semantic Relationships in Neural Word Embeddings

Constructing distributed representations for words through neural language models and using the resulting vector spaces for analysis has become a crucial component of natural language processing (NLP). But, despite their widespread application, little is known about the structure and properties of these spaces. To gain insights into the relationship between words, the NLP community has begun to adapt high-dimensional visualization techniques. Particularly, researchers commonly use t-distributed stochastic neighbor embeddings (t-SNE) and principal component analysis (PCA) to create two-dimensional embeddings for assessing the overall structure and exploring linear relationships (e.g., word analogies), respectively. Unfortunately, these techniques often produce mediocre or even misleading results and cannot address domain-specific visualization challenges that are crucial for understanding semantic relationships in word embeddings. We introduce new embedding techniques for visualizing semantic and syntactic analogies, and the corresponding tests to determine whether the resulting views capture salient structures. Additionally, we introduce two novel views for a comprehensive study of analogy relationships. Finally, we augment t-SNE embeddings to convey uncertainty information in order to allow a reliable interpretation. Combined, the different views address a number of domain-specific tasks difficult to solve with existing tools.

97 MATHEMATICS AND COMPUTING↗

Solving equilibrium problems using extended mathematical programming

We introduce an extended mathematical programming framework for specifying equilibrium problems and their variational representations, such as generalized Nash equilibrium, multiple optimization problems with equilibrium constraints, and (quasi-) variational inequalities, and computing solutions of them from modeling languages. We define a new set of constructs with which users annotate variables and equations of the model to describe equilibrium and variational problems. Our constructs enable a natural translation of the model from one formulation to another more computationally tractable form without requiring the modeler to supply derivatives. In the context of many independent agents in the equilibrium, we facilitate expression of sophisticated structures such as shared constraints and additional constraints on their solutions. We define shared variables and demonstrate their uses for sparse reformulation, economic equilibrium problems sharing economic states, mixed pricing behavior of agents, and so on. We give some equilibrium and variational examples from the literature and describe how to formulate them using our framework. Experimental results comparing performance of various complementarity formulations for shared variables are provided. Our framework has been implemented and is available within GAMS/EMP.

Equilibrium programming↗

Coreii - Scout

COREII Scout employs React, Vite, TypeScript, Tailwind, and Daisy UI for its graphical user interface (GUI), offering both dark and light modes. The code is modular, with components and reusable wrappers to enhance efficiency. The primary goal of COREII Scout is to aid analysts in collecting and analyzing various sources related to cyber attacks, utilizing models to automate the report writing process. It uses Named Entity Recognition (NER), a type of Natural Language Processing (NLP), to extract key entities from each source. Analysts review and classify these entities using the COREII Attack Chain Estimator (ACE), adding their comments. Ultimately, a Large Language Model (LLM) generates a detailed report with user guidance. This setup ensures a streamlined and effective approach to cyber attack analysis and reporting.

Pluth, Adam [Idaho National Laboratory (INL), Idah↗