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 271 records · Page 15

VWC-BERT: Scaling Vulnerability–Weakness–Exploit Mapping on Modern AI Accelerators

Defending cybersystems needs accurate mapping of software and hardware vulnerabilities to generalized descriptions of weaknesses, and weaknesses to exploits. These mappings enable cyber defenders to build plans for effective defense and assessment of potential risks to a cybersystem. With close to 170k vulnerabilities, manual mapping is not a feasible option. However, automated mapping is challenging due to limited training data, computational intractability, and limitations in computational natural language processing. Tools based on breakthroughs in Transformer-based language models have been demonstrated to classify vulnerabilities with high accuracy. We make three key contributions in this paper: (1) We present a new framework, \VWCBERT, that augments the Transformer-based hierarchical multi-class classification framework of Das et al. (\textsc{V2W-BERT}) with the ability to map weaknesses to exploits. (2) We implement \VWCBERT~ on modern AI accelerator platforms using two data parallel techniques for the pre-training phase and demonstrate nearly linear speedups across NVIDIA and Graphcore accelerator platforms. We observe nearly linear speedups for up to 16 V100 and 8 A100 GPUs, and about 3.4$\times$ speedup for A100 relative to V100 GPUs. We also observe excellent speedups on Graphcore, with $5.7\times$ speedup on 128 IPUs relative to 16 IPUs. Enabled by scaling, we also demonstrate higher accuracy using a larger language model, RoBERTa-Large. We show up to 87\% accuracy for strict and up to 98\% accuracy for relaxed classification. (3) We develop a novel parallel link manager for the link prediction phase and demonstrate up to 21$\times$ speedup with 16 V100 GPUs relative to one V100 GPU, and thus reducing the runtime from 2.5 hours to 10 minutes. We believe that generalizability and scalability of \VWCBERT~ will benefit both the theoretical development and practical deployment of novel cyberdefense solutions and vulnerability classification.

Das, Siddhartha Shankar↗

Model Predictive Control of HVAC Systems: Implementation and Testing at the University of California, Merced

A Model Predictive Control algorithm was developed for the UC Merced campus chilled water plant. Model predictive control (MPC) is an advanced control technology that has proven successful in the chemical process industry and other industries. The main goal of the research was to demonstrate the practical and commercial viability of MPC for optimization of building energy systems. The control algorithms were developed and implemented in MATLAB, allowing for rapid development, performance, and robustness assessment. The UC Merced chilled water plant includes three water-cooled chillers and a two million gallon chilled water storage tank. The tank is charged during the night to minimize on-peak electricity consumption and take advantage of the lower ambient wet bulb temperature. The control algorithms determined the optimal chilled water plant operation including chilled water supply (CHWS) temperature set-point, condenser water supply (CWS) temperature set-point and the charging start and stop times to minimize a cost function that includes energy consumption and peak electrical demand over a 3-day prediction horizon. A detailed model of the chilled water plant and simplified models of the buildings served by the plant were developed using the equation-based modeling language Modelica. Steady state models of the chillers, cooling towers and pumps were developed, based on manufacturers performance data, and calibrated using measured data collected and archived by the control system. A detailed dynamic model of the chilled water storage tank was also developed and calibrated. Simple, semi-empirical models were developed to predict the temperature and flow rate of the chilled water returning to the plant from the buildings. These models were then combined and simplified for use in a model predictive control algorithm that determines the optimal chiller start and stop times and set-points for the condenser water temperature and the chilled water supply temperature. The report describes the development and testing of the algorithm and evaluates the resulting performance, concluding with a discussion of next steps in further research. The experimental results show a small improvement in COP over the baseline policy but it is difficult to draw any strong conclusions about the energy savings potential for MPC with this system only four days of suitable experimental data were obtained once correct operation of the MPC system had been achieved. These data show an improvement in COP of 3.1% {+-} 2.2% relative to a baseline established immediately prior to the period when the MPC was run in its final form. This baseline includes control policy improvements that the plant operators learned by observing the earlier implementations of MPC, including increasing the temperature of the water supplied to the chiller condensers from the cooling towers. The process of data collection and model development, necessary for any MPC project, resulted in the team uncovering various problems with the chilled water system. Although it is difficult to quantify the energy savings resulting from these problems being remedied, they were likely on the same order as the energy savings from the MPC itself. Although the types of problems uncovered and the level of energy savings may differ significantly from other projects, some of the benefits of detecting and diagnosing problems are expected from the use of MPC for any chilled water plant. The degree of chiller loading was found to be a key factor for efficiency. It is more efficient to operate the chillers at or near full load. In order to maximize the chiller load, one would maximize the temperature difference across chillers and the chilled water flow rate through the chillers. Thus, the CHWS set-point and the chilled water flow-rate can be used to limit the chiller loading to prevent chiller surging. Since the flow rate has an upper bound and the CHWS set point has a lower bound, the chiller loading is constrained and often determined by the chilled water return temperature (CHWR). The CHWR temperature is primarily comprised of warm water from the top of the TES tank. The CHWR temperature falls substantially as the thermocline approaches the top of the tank, which reduces the chiller loading. As a result, it has been determined that overcharging the TES tank can be detrimental to the chilled water plant efficiency. The resulting MPC policy differs from the current practice of fully charging the TES tank. A heuristic rule could possible avoid this problem without using predictive control. Similarly, the COP improvements from the change in CWS set-point were largely captured by a static set-point change by the operators. Further research is required to determine how much of the MPC savings could be garnered through simplified rules (based on the MPC study), with and without prediction.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Neurons to algorithms LDRD final report.

Over the last three years the Neurons to Algorithms (N2A) LDRD project teams has built infrastructure to discover computational structures in the brain. This consists of a modeling language, a tool that enables model development and simulation in that language, and initial connections with the Neuroinformatics community, a group working toward similar goals. The approach of N2A is to express large complex systems like the brain as populations of a discrete part types that have specific structural relationships with each other, along with internal and structural dynamics. Such an evolving mathematical system may be able to capture the essence of neural processing, and ultimately of thought itself. This final report is a cover for the actual products of the project: the N2A Language Specification, the N2A Application, and a journal paper summarizing our methods.

Rothganger, Fredrick H.↗

TRuML

Kappa and BioNetGen (BNGL) are prominent rule-based modeling languages for representing complex biochemical reaction networks. Each language is distributed with a distinct software suite and modelers may wish to take advantage of both toolsets. This application, TRuML, translates models written in either Kappa or BNGL into the other language. While similar in many respects, key differences between the two languages makes translation sufficiently complex that automation becomes a useful tool. TRuML accommodates the languages' complexities and produces a semantically equivalent model in the alternate language of the input model when possible, and an approximate model in certain other cases.

Hlavacek, William↗

FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

SCIMON: Scientific Inspiration Machines Optimized for Novelty

We explore and enhance the ability of neu- ral language models to generate novel scien- tific directions grounded in literature. Work on literature-based hypothesis generation has traditionally focused on binary link prediction— severely limiting the expressivity of hypothe- ses. This line of work also does not focus on optimizing novelty. We take a dramatic depar- ture with a novel setting in which models use as input background contexts (e.g., problems, experimental settings, goals), and output natu- ral language ideas grounded in literature. We present SCIMON, a modeling framework that uses retrieval of “inspirations” from past scien- tific papers, and explicitly optimizes for novelty by iteratively comparing to prior papers and up- dating idea suggestions until sufficient novelty is achieved. Comprehensive evaluations reveal that GPT-4 tends to generate ideas with over- all low technical depth and novelty, while our methods partially mitigate this issue. Our work represents a first step toward evaluating and developing language models that generate new ideas derived from the scientific literature.

Ji, Heng↗

Privacy-Aware RAG-Enabled LLMs for Collaborative AI in Organizations

Recent advancements in Large Language Models (LLMs) based on Transformer architectures have significantly improved capabilities in natural language processing and generation. However, deploying LLMs for inter-organizational communication poses challenges, in ensuring privacy and facilitating effective collaboration. This paper introduces a novel decentralized inference meta-agent chatbot that leverages privacy-aware Retrieval-Augmented Generation (RAG)-enabled LLMs for collaborative AI communication across organizations. Built on Microsoft’s Autogen, the platform enables LLMs to autonomously refine responses, enhancing accuracy and relevance. It incorporates advanced hallucination mitigation techniques using Uptrain and a privacy-focused RAG framework that employs synthetic document generation to protect sensitive information. Comprehensive evaluations demonstrate the platform’s effectiveness in maintaining contextual relevance and stringent privacy standards, effectively addressing critical challenges in LLM-enhanced collaborative AI communication. This work represents a significant step toward secure and efficient inter-organizational collaboration using advanced generative AI technologies.

97 - MATHEMATICS AND COMPUTING↗

LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages

The rapid evolution of large language models (LLMs) has opened new possibilities for automating various tasks in software development. This paper evaluates the capabilities of the LLaMA 2-70B model in automating these tasks for scientific applications written in commonly used programming languages. Using representative test problems, we assess the model's capacity to generate code, documentation, and unit tests, as well as its ability to translate existing code between commonly used programming languages. Our comprehensive analysis evaluates the compilation, runtime behavior, and correctness of the generated and translated code. Additionally, we assess the quality of automatically generated code, documentation, and unit tests. Here, our results indicate that while LLaMA 2-70B frequently generates syntactically correct and functional code for simpler numerical tasks, it encounters substantial difficulties with more complex, parallelized, or distributed computations, requiring considerable manual corrections. We identify key limitations and suggest areas for future improvements to better leverage AI-driven automation in scientific computing workflows.

97 MATHEMATICS AND COMPUTING↗

Autogenerating a Domain-Specific Question-Answering Data Set from a Thermoelectric Materials Database to Enable High-Performing BERT Models

We present a method for autogenerating a large domain-specific question-answering (QA) dataset from a thermoelectric materials database. We show that a small language model, BERT, once fine-tuned on this automatically generated dataset of 99,757 QA pairs about thermoelectric materials, affords better performance in the field of thermoelectric materials compared to a BERT model fine-tuned on the generic English-language QA data set, SQuAD-v2. We further show that mixing the two data sets (ours and SQuAD-v2), which have significantly different syntactic and semantic scopes, allows the BERT model to achieve even better performance. The best-performing BERT model fine-tuned on the mixed data set outperforms the models fine-tuned on the other two data sets by scoring an exact match of 67.93% and an F1 score of 72.29% when evaluated on our test data set. This has important implications as it demonstrates the ability to realize high-performing small language models, with modest computational resources, empowered by domain-specific materials data sets which can be generated according to our method.

biological databases↗

Using Artificial Intelligence to Improve Reliability and Operational Efficiency of Small-Scale Hydroelectric Distributed Generation

Reliability and resilience are critical concerns for distributed generation (DG) at the rural electric level. The integration of renewable energy sources, such as small-scale hydroelectric distributed generators (hydro DGs), introduces operational challenges, particularly regarding aging infrastructure and grid stability. Artificial Intelligence (AI)-driven Machine Learning (ML) models and applications of Large Language Models (LLMs) offer promising solutions for optimizing DG operations and enhancing resilience. This paper explores AI-based models for improving efficiency, fault resolution, and outage mitigation in small-scale hydro DGs. Furthermore, it highlights the development of a centralized, AI-powered information portal for rural electric cooperatives and municipalities. The research evaluates hydro DG plant models and discusses the applicability of AI-powered question-answering tools for real-time operations, focusing on statistical data, load flow, voltage regulation, and generation power. The findings demonstrate AI’s potential to transform DG management to ensure greater stability and resilience in rural electric grids.

Bhattacharyya, Arjun [ORNL] (ORCID:000900060976046↗

RuleBuilder

RuleBuilder is a tool for drawing graphs represented by the BioNetGen rule-based modeling language (BNGL), a domain-specific language used to formulate mathematical models of biochemical interaction networks. This framework provides an intuitive plain-text representation of such networks using a graph-based formalism. The interactions between the model's components are graph-rewriting rules that denote the minimum context needed for the interaction to occur. In some cases the context required for reactions to occur can grow quite large, and the lengthy textual description of the interaction can be difficult to interpret or debug. RuleBuilder is designed to make this process simpler through visualization of individual rule or pattern strings. The software assists in the reading of existing models by converting the BNGL strings of interest into a graph-based representation composed of nodes and edges. RuleBuilder also enables the user to build the visual representation directly from its interface, composing the BNGL string as components and operators are added to the graphical object.

Fricke, Matthew↗

What Is the Agent Doing? Visualizing Agentic AI Querying Workflows

We explore how visualizations can help users understand what an AI agent is doing as it builds and runs queries over data. As part of the LinkQ system, a natural language interface for querying knowledge graphs with a large language model (LLM), we designed two complementary views: A State Diagram that shows where the agent is within a larger workflow, and a Live Action Display that gives real-time updates about the agent's current task. In a study with 14 practitioners, we found that these visuals helped participants build stronger mental models of the agent's behavior while also increasing their confidence in the system. However, we also observed that users sometimes trusted incorrect outputs simply because the agent appeared to be doing the "right" thing. Our findings point to both the value and risk of visualizing agent behavior in interactive AI systems.

97 MATHEMATICS AND COMPUTING↗

ChemGraph as an agentic framework for computational chemistry workflows

Atomistic simulations are essential in chemistry and materials science but remain challenging to run due to the expert knowledge required for the setup, execution, and validation stages of these calculations. We present ChemGraph, an agentic framework powered by artificial intelligence and state-of-the-art simulation tools to streamline and automate computational chemistry and materials science workflows. ChemGraph leverages graph neural network-based foundation models for accurate yet computationally efficient calculations and large language models (LLMs) for natural language understanding, task planning, and scientific reasoning to provide an intuitive and interactive interface. We evaluate ChemGraph across 13 benchmark tasks and demonstrate that smaller LLMs (GPT-4o-mini, Claude-3.5-haiku, Qwen-2.5-14B) perform well on simple workflows, while more complex tasks benefit from using larger models. Importantly, we show that decomposing complex tasks into smaller subtasks through a multi-agent framework enables GPT-4o to reach perfect accuracy and smaller LLMs to match or exceed single-agent GPT-4o's performance in these benchmarks.

Computational chemistry↗

GridCoPilot for Thermal Events: An LLM-Based Platform for Power Grid Reliability Analysis

Large Language Models show promise for translating natural language into database queries, but deploying such systems in safety-critical domains requires high reliability. We present an application of GridCoPilot to thermal event analysis (heatwaves and coldwaves) that affect power grid reliability. Our approach uses a LangChain SQL Agent to translate natural language queries into auditable SQL statements, with deterministic visualization routines that parse the structured query results. We introduce structural framing as a design principle, we integrate a NERC-region-level event library with county-level meteorology and decompose the combined data into three relational tables (event metadata, county-level event details, and a county-to-NERC subregion mapping), using prompt-guided joins to direct the model toward correct multi-table queries. For two core analytical patterns (identifying worst events by region and by region-year), the system achieved 100% SQL accuracy across all 16 NERC subregions and both event types (64 queries total). These results validate the approach for target use cases, though performance on diverse natural language formulations requires further investigation. We discuss design trade-offs, failure modes including JSON output truncation, and pathways for extending this approach to other hazard domains.

24 POWER TRANSMISSION AND DISTRIBUTION↗

VISION: a modular AI assistant for natural human-instrument interaction at scientific user facilities

Scientific user facilities, such as synchrotron beamlines, are equipped with a wide array of hardware and software tools that require a codebase for human-computer-interaction. This often necessitates developers to be involved to establish connection between users/researchers and the complex instrumentation. The advent of generative AI presents an opportunity to bridge this knowledge gap, enabling seamless communication and efficient experimental workflows. Here we present a modular architecture for the Virtual Scientific Companion by assembling multiple AI-enabled cognitive blocks that each scaffolds large language models (LLMs) for a specialized task. With VISION, we performed LLM-based operation on the beamline workstation with low latency and demonstrated the first voice-controlled experiment at an x-ray scattering beamline. The modular and scalable architecture allows for easy adaptation to new instruments and capabilities. Development on natural language-based scientific experimentation is a building block for an impending future where a science exocortex—a synthetic extension to the cognition of scientists—may radically transform scientific practice and discovery.

36 MATERIALS SCIENCE↗

PRIME: An evaluation framework for protein representation inference and generalization in viral mutation space

Background Protein language models (PLMs) have revolutionized protein fitness prediction, yet their application to rapidly evolving viral pathogens is often confounded by extreme sequence homology. This homology leads to “data leakage” in standard random validation splits, yielding inflated performance metrics that fail to translate into real-world biosurveillance utility. Results We present Protein Representation Inference for Mutation Evaluation (PRIME), a framework that integrates domain-specific fine-tuning with a rigorous position-stratified validation protocol to evaluate viral threats. Using a dataset of 347,432 SARS-CoV-2 receptor binding domain (RBD) sequences, we demonstrate that while random training data split yields deceptive R 2 values (> 0.90), they fail to generalize to novel mutational sites. By benchmarking models up to 650 M parameters, we show that domain-specific fine-tuning of the ESM-C 600 M model with correctly stratified data provides an initial demonstration of predictive signal for binding affinity and expression at unseen mutational sites of binding affinity and expression on unseen sites (R 2 ~0.23), a significant advancement over base foundation models which exhibit no predictive power (R 2 <0). PRIME’s embedding-based clustering identified 3.03% of bat coronavirus sequences as candidates for further experimental prioritization based on their functional similarity to human-infective strains in embedding space, offering a perspective complementary to traditional phylogenetic methods. Conclusion PRIME establishes a new benchmark for the application of PLMs in pathogen surveillance. Our findings demonstrate that state-of-the-art models and fine-tuning, when paired with stratified validation, provide biologically meaningful insights into pathogen evolution and zoonotic risk.

59 BASIC BIOLOGICAL SCIENCES↗