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.

SourceResearch connectionFrom yearThrough year

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

At least 559 records · Page 31

All sources NASA NTRS DOE OSTI

NASA NTRSDate not supplied

Kaona: Deep Searching and Curating Data from Aviation Safety Reporting Systems

Context: Several works in the literature have examined how safety narrative databases can be leveraged to share lessons learned. However, less attention has been given to augmenting existing processes for mining these safety reporting system databases. Aim: In this work, we introduce Kaona: An interface that weaves machine learning in existing aviation safety database mining activities. Method: We provide a use case of search, curation and newsletter writing to showcase how Kaona features build on existing processes and on its own to enhance information retrieval, curation and synthesis of narratives. Results: We created two instances of Kaona internally for evaluation, one using publicly available NASA’s ASRS narratives and another using publicly available C3RS narratives. Data ranged from 1998 to 2024. Conclusion: Our tool provides a new way to explore safety narratives, serving to re-imagine how text databases can benefit of novel information retrieval mechanisms in the era of large language models.

ASRS↗

NASA NTRSDate not supplied

Kaona: Deep Searching and Curating Aviation Safety Reporting Systems

Context: Several works in the literature have examined how safety narrative databases can be leveraged to share lessons learned. However, less attention has been given in augmenting existing processes of safety reporting systems. Aim: In this work, we introduce Kaona: An interface that weaves machine learning in existing aviation safety reporting systems activities. Method: We provide a use case of search, curation and newsletter writing to showcase how Kaona features build on existing processes and on its own to enhance information retrieval, curation and synthesis of narratives. Results: We created two instances of Kaona internally for evaluation, one using all public NASA's ASRS narratives and another using all public C3RS narratives. Data ranged from 1998 to 2024. Conclusion: Our tool provides a new way to explore safety narratives, serving to re-imagine how text databases can benefit of novel information retrieval mechanisms in the era of large language models.

asrs↗

NASA NTRSDate not supplied

Towards Functional Hazard Assessment (CFHA): A Gap Analysis and Concept for Emerging Aviation Systems

Given the current evolution of the National Airspace and future trajectory towards novel and evolving operations with varying levels of autonomy, complexity, and acceptable risk, there is an opportunity to support safety assurance by extending existing methodologies, such as Functional Hazard Assessment (FHA). In response to challenges in performing FHA for novel aviation concepts, we propose a concept for Computational Functional Hazard Assessment (CFHA), which provides processes, methods, and tools for incorporating external data to facilitate further exploration of the hazard space iterativelty throughout the design process. The core components of CFHA involve knowledge capture from historical and operational data, functional architecture specification via a formal modeling language, and simulation for hazardous scenario analysis. Through this concept, we aim to adapt conventional safety assessment to address the increasingly complex hazard space generated from emerging operations.

Seydou Mbaye↗

NASA NTRSDate not supplied

Kaona: Deep Searching and Curating Safety Reporting Systems

asrs↗

NASA NTRSDate not supplied

LLMs and GenAI Tools to Depict Contributions of Human Systems to Spaceflight Tasks Execution

Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) technologies, particularly Large Language Models (LLMs) capable of sophisticated syntax analysis, offer substantial potential in automating complex processes, thereby saving time and human resources. This study explores the development of an LLM-driven model designed to analyze and categorize a diverse set of Mars mission tasks into 18 predefined Human System Task Categories (HSTCs) based on their textual descriptions. As part of developing the Crew Health and Performance – Probabilistic Risk Assessment (CHP-PRA projects Performance Risk Model (PRisM) proof-of-concept, we established a framework to project performance scores from small-scale tests onto a preliminary list of Mars tasks. The foundation of our model was a comprehensive spreadsheet populated by NASA experts and clinicians, which detailed each Mars task alongside binary indicators of HSTC involvement. This dataset enabled the initial application of supervised ML, training and testing on existing HSTC labels. The HSTCs were originally defined from a medical system perspective, focusing on task impairments due to deteriorated human health. To expand our model's scope to include categories impacting performance, we face the challenge of generating binary labels (0 or 1) for new categories without pre-existing data. We address this by employing Generative AI (GenAI) software to determine whether a given task involved a new category by asking, "Does task A involve using category B?" We validate our approach by comparing the GenAI's binary classifications with the expert-provided labels for existing HSTCs. Notably, we utilize Ollama [4], a locally hosted GenAI tool that does not require cloud access, thus safeguarding NASA's proprietary data from unauthorized exposure. This study demonstrates the feasibility of leveraging cutting-edge AI tools to advance research, paving the way for automation and rapid decision-making in space exploration.

Mona Matar↗

NASA NTRSDate not supplied

AI Curation Methods for NASA Scientific Data

The NASA Open Science Data Repository (OSDR) serves as a central hub for sharing and accessing NASA's vast collection of scientific data, supporting researchers across diverse fields. To enhance the efficiency, accuracy, and accessibility of this data, we are leveraging advanced artificial intelligence (AI) techniques as part of the AI for Curation project. By integrating large language models (LLMs) into our data curation workflow, we aim to streamline the entire process—from data submission to user interaction. This initiative focuses on improving key areas, including data ingestion, curation, and user engagement with curated datasets, impacting multiple domains and a wide user base. First, we are developing tools that can automatically parse data in various formats, using LLMs to convert unstructured data into structured, standardized formats. This reduces the manual effort required for curation, allowing curators to focus on more critical scientific analyses. Additionally, AI and machine learning (ML) models are being implemented to automate data validation and verification, ensuring the highest standards of data quality and reliability. Finally, we are creating a conversational AI agent to interact with the curated scientific studies in OSDR, helping users easily navigate the repository and access relevant data. By enhancing data discoverability and accessibility, these advancements will foster new research opportunities and promote the principles of open science.

Walter Alvarado↗

DOE OSTI2024

Powering Data Centers with Clean Energy: A Techno-Economic Case Study of Nuclear and Renewable Energy Dependability

Rising data demands from artificial intelligence (AI) and large language models (LLMs) generating images, videos, and text have prompted increased need for larger and more robust data centers in the United States. Major companies interested in these larger data centers face the choice of linking them to existing regional grids, building stand-alone power supplies onsite, or a combination of both. The request, review, and approval process for new transmission lines to grids in the United States, however, has grown in recent years to times spans rivaling those of new construction for nuclear power plants. Building an islanded power supply for each data center is therefore becoming a prominent option. In this case study, several technologies are modeled in techno-economic simulations for long-term system costs subject to fixed electricity demand from a singular data center. A 250 MWe data center is assumed with additional 50 MWe for resiliency. Techno-economic simulations are conducted using the Holistic Energy Resource Optimization Network (HERON) software, which is a part of the Framework for Optimization of Resources and Economics (FORCE) tool suite. Technologies considered include solar, wind, lithium-ion batteries, and several types of nuclear reactors: large-scale reactors, small modular reactors, and microreactors. A low- and high-cost estimate for each technology is assumed to develop a range of expected economic performance. Low-cost estimates included several clean energy production tax credits. Different combinations of renewable energy generators with nuclear reactors are considered, ranging from a fully renewable-powered data center to a fully nuclear-powered data center. Historic time series of wind and solar availability from the Texas grid are used to train a reduced order model; this model then generates unique time series with similar characteristics of the training dataset. Multiple scenarios of weather and subsequent operations are simulated for each renewable-nuclear combination to determine total costs throughout the project lifetime. Fully renewable-powered configurations required large amounts of installed capacity (GW scale) in the simulations to meet the fixed demand of the data center. This is due to some scenarios in the historical dataset which captured low-wind and low-solar days, requiring over-building of these technologies as well as batteries to compensate for the low amounts of electricity generation. Fully nuclear-powered configurations outperformed the fully renewable and mixed renewable-nuclear configurations in terms of cost, with ranges between $1B and $10B in 2023 USDs compared to $40B+ for fully renewable configurations. Of the nuclear technologies, small modular reactors performed better economically than large-scale nuclear models due to lower projected capital costs, and both performed better than the microreactor models. These results demonstrate the applicability of firm, dispatchable electricity resources from baseload generators like nuclear power plants for operating facilities that run at constant power without daily variability.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2024

Towards Agentic AI on Particle Accelerators

As particle accelerators grow in complexity, traditional control methods face increasing challenges in achieving optimal performance. This paper envisions a paradigm shift: a decentralized multi-agent framework for accelerator control, powered by Large Language Models (LLMs) and distributed among autonomous agents. We present a proposition of a self-improving decentralized system where intelligent agents handle high-level tasks and communication and each agent is specialized control individual accelerator components. This approach raises some questions: What are the future applications of AI in particle accelerators? How can we implement an autonomous complex system such as a particle accelerator where agents gradually improve through experience and human feedback? What are the implications of integrating a human-in-the-loop component for labeling operational data and providing expert guidance? We show two examples, where we demonstrate viability of such architecture.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

Reducing AI RAG Hallucination by Optimizing Routing Techniques

Large Language Models (LLMs), such as ChatGPT, tend to “hallucinate”, meaning they confidently generate false information. Retrieval Augmented Generation (RAG) attempts to diminish hallucination by providing context to the LLM from data stores (indexes) containing relevant information. The LLM uses this context to formulate its response. RAG systems can still suffer from hallucination because of bad embeddings or ineffective routing. For example, a router will often return context from an irrelevant index, resulting in a hallucinated answer. In this study, we aim to minimize the frequency of routing hallucinations by optimizing Index Summary Routing.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Automation of Vulnerability and Patch Management: Information Extraction, Association, and Optimization

Vulnerability and patch management is an integral part of a robust cybersecurity program, yet it grows increasingly complex due to the sheer amount of data that must be analyzed. Particularly in Operational Technology (OT) environments, analysis must be done manually because of the lack of automated solutions. Additionally, there are many steps in this process, from the initial discovery of the vulnerability to the implementation of its remediation, and each step in the process requires different data in order to be performed effectively. In this work, we provide approaches and strategies to assist operators in industrial or OT environments throughout the vulnerability management cycle. Security advisories provide key information about mitigation strategies, or actions that can be taken when a patch is unavailable or cannot be installed. Details of these strategies are not shared in public vulnerability databases and must be found manually. We approach this problem by designing a solution to automatically identify that information within vendor security advisories and retrieve it for operator use. We start with an approach that requires domain-specific knowledge of certain frequently-seen reference websites. Next, an approach that can work on an arbitrary website but relies on certain keywords. Finally, an approach that uses Natural Language Processing (NLP) methods and does not require specific knowledge or keywords. Each of these approaches is more general than its predecessor; we demonstrate high accuracy for all approaches Advisories also often contain details of affected products in non-standard or natural language formats. While this information can be easily understood when read by an operator, the non-standard format acts as a barrier to effective automation. We provide an approach for the first step in this process: identifying vendors in security advisories and mapping them to a standard framework for representing digital assets and software products. We evaluate five established string similarity algorithms, plus one of our own design that combines string similarity and information theory, on the task of mapping vendors to their corresponding entries in the Common Platform Enumeration (CPE) repository. Our results show that our proposed metric outperforms all others. Due to the constraints on time, finances, and personnel for organizations, Large Language Models (LLMs) may seem like attractive opportunities for security operators to speed up information gathering; however, it is still not clear whether LLMs can handle vulnerability management tasks well. To answer this question, we perform an empirical study of LLMs’ ability to provide consistent, accurate information about vulnerabilities in order to guide organizations in their adoption of LLMs. We observe poor performance for all models tested, suggesting that these models are not well-suited to the consistent retrieval of accurate vulnerability information. Finally, once vulnerabilities have been identified and any additional information has been obtained, operators must decide which remediation actions to implement based on their available resources. This already-complex problem becomes even more so when we consider that a vulnerability may have multiple avenues for remediation. We formulate this scenario as two knapsack problems and provide solutions, which we then compare against several existing strategies for vulnerability prioritization seen in real operational environments.

McClanahan, Kylie↗

DOE OSTI2025

HEPTAPOD: Orchestrating High Energy Physics Workflows Towards Autonomous Agency

Many workflows in high-energy-physics (HEP) stand to benefit from recent advances in transformer-based large language models (LLMs). While early applications of LLMs focused on text generation and code completion, modern LLMs now support orchestrated agency: the coordinated execution of complex, multi-step tasks through tool use, structured context, and iterative reasoning. We introduce the HEP Toolkit for Agentic Planning, Orchestration, and Deployment (HEPTAPOD), an orchestration framework designed to bring this emerging paradigm to HEP pipelines. The framework enables LLMs to interface with domain-specific tools, construct and manage simulation workflows, and assist in common utility and data analysis tasks through schema-validated operations and run-card-driven configuration. To demonstrate these capabilities, we consider a representative Beyond the Standard Model (BSM) Monte Carlo validation pipeline that spans model generation, event simulation, and downstream analysis within a unified, reproducible workflow. HEPTAPOD provides a structured and auditable layer between human researchers, LLMs, and computational infrastructure, establishing a foundation for transparent, human-in-the-loop systems.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗

DOE OSTI2025

AUTOMATIC GENERATION OF EVENT TREES AND FAULT TREES: A MODEL-BASED APPROACH

In the past few decades, increasing complexity in modern engineering systems has been driven by the integration of a large number of components and by the fact that the system operations involve many disciplines (e.g., thermal-hydraulics, plant operations, cyber-security). Current safety/reliability modeling approaches to such systems are labor intensive, difficult to learn, and rely heavily on simplistic Boolean logic to depict failure propagation and accident progression. While these methods serve well for simple systems (i.e., linear causal systems with limited small inter- and intra-system interactions), their results are difficult to verify when modeling complex systems (typically performed through the extensive use of modeling assumptions). The development of new methods is addressed to meet these challenges through a model-based system engineering (MBSE) lens. Under MBSE philosophy, every aspect of the system (form or function) is represented by a model that completely characterizes its architecture or behavior. MBSE approach greatly improves the management of design, analysis and verification of complex systems. An integration of Dynamic Probabilistic Risk Assessment (DPRA) methods with MBSE models is proposed to perform safety/reliability analyses of engineering systems. In particular, MBSE representation of the system (performed using Systems Modeling Language [SysML]) is coupled with DPRA methods to automatically generate event trees and fault trees.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2025

AI for Interpreting Nuclear Power Plant Documents for Power Uprates

To reduce the cost and time needed for regulatory compliance, nuclear power plants (NPPs) can utilize artificial intelligence (AI) to assist in interpreting complex and voluminous documents that typically span thousands of pages. Usually, the process of interpreting a plant’s technical specifications (TSs) and associated documents is labor intensive. This study aims to understand what processes state-of-the-art large language models (LLMs) can automate and to identify the pitfalls associated with using LLMs to reduce human labor costs and time. This research uses a recent AI technology called retrieval augmented generation (RAG), which retrieves pages of information from TSs and associated documents to assist with NPP power uprates (cleared to produce more power). LLMs are integral to RAG because they create human-like responses based on the retrieved information, aiding in the interpretation and application processes. A baseline case demonstrates how LLMs can operate successfully for a power uprate application. Then five use cases show five types of potential failures: (1) RAG retrieving the incorrect information, (2) RAG misinterpreting the retrieved information, (3) RAG relying on knowledge not contained in the retrieved information, (4) RAG hallucinating, and (5) RAG refusing to answer. The results of the five use cases suggest that automating the human interpretation of TSs and associated documents with AI should be approached with caution. A subject-matter expert reviewed the AI outputs from the five use cases and concluded that an LLM can produce technical information that is needed to produce power uprate applications in certain instances.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗

DOE OSTI2026

Resource-Adaptive Federated Text Generation with Differential Privacy

In cross-silo federated learning (FL), sensitive text datasets remain confined to local organizations due to privacy regulations, making repeated training for each downstream task both communication-intensive and privacy-demanding. A promising alternative is to generate differentially private (DP) synthetic datasets that approximate the global distribution and can be reused across tasks. However, pretrained large language models (LLMs) often fail under domain shift, and federated finetuning is hindered by computational heterogeneity: only resource-rich clients can update the model, while weaker clients are excluded, amplifying data skew and the adverse effects of DP noise. We propose a flexible participation framework that adapts to client capacities. Strong clients perform DP federated finetuning, while weak clients contribute through a lightweight DP voting mechanism that refines synthetic text. To ensure the synthetic data mirrors the global dataset, we apply control codes (e.g., labels, topics, metadata) that represent each client’s data proportions and constrain voting to semantically coherent subsets. This two-phase approach requires only a single round of communication for weak clients and integrates contributions from all participants. Experiments show that our framework improves distribution alignment and downstream robustness under DP and heterogeneity.

Wang, Jiayi [ORNL]↗

DOE OSTI2026

REFSafE: A RAG-Enabled Framework for Predictive Risk Analysis and Automated Safety Report Generation in Mission-Critical Environments

Operational safety in mission-critical environments requires AI systems that are accurate, interpretable, and resistant to hallucination. We present an agentic Retrieval-Augmented Generation (RAG) framework, REFSafe, for grounded hazard analysis and automated safety report generation. The system integrates Large Language Models (LLMs) with structured operational data, historical incident repositories, policy documents, and external authoritative sources. Through iterative agentic reasoning, the framework retrieves, verifies, and synthesizes evidence prior to generation, enforcing citation-backed outputs with explicit source attribution (documents, links, and prior events) to ensure traceability and trust. To mitigate hallucinations and unsupported claims, all risk assessments and forecasts are constrained to retrieved evidence, with confidence signals derived from retrieval relevance and source consistency. A transparent pipeline enables subject matter experts (SMEs) to validate predictions, and provide structured feedback, forming a continuous performance calibration loop. Preliminary deployment demonstrates improved reliability in hazard detection and safety/vulnerability report generation. This work advances trustworthy, evidence-grounded AI for predictive safety intelligence in mission-critical operations.

Das, Sanjay [ORNL] (ORCID:0009000542591915)↗

DOE OSTI2026

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation

Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipelines ability to ingest several modalities of information. We present (1) a curated dataset of 93 questions designed to evaluate a pipeline's ability to ingest textual data, tables, images, multimodal data, and cross-document multimodal data; (2) a phrase-level recall metric for correctness; (3) a nearest-neighbor embedding classifier in an attempt to classify pipeline hallucinations; (4) a comparative evaluation of 2 pipelines built with open-source retrieval mechanisms and 4 closed-source foundational models; and (5) a third-party human evaluation of the alignment of our correctness and hallucination metrics. We find that closed-source pipelines significantly outperform open-source pipelines in both the correctness and halucination metrics, with a wider performance gap in questions relying on multimodal and cross-document information. We also find after a human evaluation of our correctness and hallucination metric compared with our questions and pipeline responses, average agreement was 4.62 for correctness 4.53 for hallucination detection on a 1-5 Likert scale with 5 being strongly agree with our determination.

Hildebrand, Samuel [ORNL] (ORCID:0009000465963104)↗

DOE OSTI2026

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems demand reliable hazard identification. While large language models (LLMs) have shown promise in automating safety analysis tasks, single-turn, monolithic inference is brittle: it lacks the self-correction, deliberation, and contextual refinement that safety engineers apply iteratively. In this paper, we introduce HAZDIAL, a framework that investigates whether structured agentic dialogue (multi-agent, multi-turn interactions) improves the quality of NLP-based hazard identification over single-pass baselines. We systematically compare two dialogue modalities: adversarial debate and constructive discussion, and propose an genetic algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and a novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing empirical evidence for dialogue-driven hazard analysis.

Das, Sanjay [ORNL] (ORCID:0009000542591915)↗

DOE OSTI2026

Reining in an Agentic Harness for High Energy Physics

Agentic systems now address tasks across theoretical, phenomenological, and experimental high energy physics (HEP), but their scientific capabilities remain difficult to reuse across different large language models, providers, and harnesses. We argue that stable parts of these workflows should be promoted into versioned scientific operations and exposed through common protocols. Existing general-purpose harnesses can then be specialized for HEP through task-specific sets of tools and skills, while community-maintained registries would make these capabilities discoverable and citable. We identify mismatches in conventions, assumptions, and domains of validity among independently developed operations as a potential obstacle to their composition, and discuss machine-readable scientific contracts as one possible solution. These design principles and evaluation guidelines provide a near-term path toward a portable and community-maintained agentic harness for HEP.

Menzo, Tony [Alabama U.; Fermilab] (ORCID:00000002↗