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 55 records · Page 3

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Evaluating the Effectiveness of Retrieval-Augmented Large Language Models in Scientific Document Reasoning

Despite the dramatic progress in Large Language Model (LLM) development, LLMs often provide seemingly plausible but not factual information, often referred as hallucinations. Retrieval-augmented LLMs provide a non-parametric approach to solve these issues by retrieving relevant information from external data sources and augment the training process. These models helps to trace evidence from an externally provided knowledge base allowing the model predictions to be better interpreted and verified. In this work, we critically evaluate these models in their ability to perform in scientific document reasoning tasks. To this end, we tuned multiple such model variants with science-focused instructions and evaluated them on a scientific document reasoning benchmark for the usefulness of the retrieved document passages. Our findings suggest that models justify predictions in science tasks with fabricated evidence and leveraging scientific corpus as pretraining data does not alleviate the risk of evidence fabrication.

• Artificial intelligence (AI) / machine learning ↗

DOE OSTI2025

A knowledge-informed large language model framework for U.S. nuclear power plant shutdown initiating event classification for probabilistic risk assessment

Identifying and classifying shutdown initiating events (SDIEs) is critical for developing shutdown probabilistic risk assessment for nuclear power plants. Existing computational approaches cannot achieve satisfactory performance due to the challenges of unavailable large, labeled datasets, imbalanced event types, and label noise. To address these challenges, we propose a hybrid pipeline that integrates a knowledge-informed machine learning model to prescreen non-SDIEs and a large language model (LLM) to classify SDIEs into four types. In the prescreening stage, we proposed a set of 44 SDIE text patterns that consist of the most salient keywords and phrases from six SDIE types. Text vectorization based on the SDIE patterns generates feature vectors that are highly separable by using a simple binary classifier. The second stage builds Bidirectional Encoder Representations from Transformers (BERT)-based LLM, which learns generic English language representations from self-supervised pretraining on a large dataset and adapts to SDIE classification by fine-tuning it on an SDIE dataset. The proposed approaches are evaluated on a dataset with 10,928 events using precision, recall ratio, F 1 score, and average accuracy. In conclusion, the results demonstrate that the prescreening stage can exclude more than 97% non-SDIEs, and the LLM achieves an average accuracy of 95.1% for SDIE classification.

99 - GENERAL AND MISCELLANEOUS↗

DOE OSTI2025

Position-Enhanced Gradient Attack (PEGA) on Medical Language Models

Federated Learning (FL) enables collaborative training of language models on sensitive clinical notes without sharing the data. However, this paradigm is vulnerable to gradient inversion attacks that can reconstruct private data from shared gradients. We find that state-of-the-art attacks are less effective in the medical domain, failing to overcome the unique challenges posed by its specialized vocabulary and unstructured format. To address this, we introduce the Position-Enhanced Gradient Attack (PEGA), a novel attack that makes gradients position-aware by optimizing token and position embeddings simultaneously. PEGA employs two key innovations: a periodic sorting of positional embeddings to resolve token order ambiguity and a late-stage embedding replacement strategy to correct hard-to-recover critical tokens. To evaluate the leakage of sensitive data more directly, we also propose the Unified PHI-Recall (UPHI), a new metric measuring the recovery of Protected Health Information. Experiments on the MIMIC-III dataset show that PEGA significantly outperforms leading attacks like TAG and LAMP, particularly in its ability to reconstruct identifiable patient information, exposing a more severe and nuanced privacy risk in federated medical NLP.

Xu, Nuo [University of Minnesota]↗

NASA NTRS2023

SafeAeroBERT: Towards a Safety-Informed Aerospace-Specific Language Model

As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the ASRS. Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about human factors, aircraft, and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.

Aviation↗

NASA NTRSDate not supplied

SafeAeroBERT: Towards a Safety-Informed Aerospace-Specific Language Model

As aviation systems continue to operate with high traffic, large amounts of documents containing safety-relevant data continue to be generated via reporting systems such as the Aviation Safety Reporting System (ASRS). Advanced natural language processing techniques, specifically pre-trained language models, have shown great success in domain-specific applications; however, the text in aviation safety reports is inundated with jargon and thus not fully utilized by general pre-trained models. In this research, we work towards developing a safety-informed aerospace-specific language model by pre-training a Bidirectional Encoder Representations from Transformer (BERT) model on reports from the Aviation Safety Reporting System and the National Transportation Safety Board. The resulting model, called SafeAeroBERT, is fine-tuned for the specific task of document classification, and can be further tuned for named-entity recognition, relation detection, information retrieval, and summarization. Results from the classification task are compared between SafeAeroBERT, the base BERT, and SciBERT models and show SafeAeroBERT outperforms the general BERT and SciBERT on classifying reports about weather and procedure. SafeAeroBERT can be used on custom tasks, not limited to document classification, and is intended to aid an intelligent knowledge manager for safety report repositories.

Aviation↗

DOE OSTI2025

Autonomous alloy composition optimization using molecular dynamics guided by a large language model

Here, we present an autonomous materials discovery framework that couples a large language model (LLM) with molecular dynamics (MD) simulations to optimize Fe–Cr–Mn alloy compositions for tensile strength. Starting from six distinct compositions, the LLM operated as an intelligent agent, iteratively proposing changes based on prior simulation results and constraints. Over 50 iterations per case, the LLM adaptively explored the composition space, identifying high-strength regions, not easily accessible by conventional methods. The highest strength, 18.7 GPa, was achieved with Fe 71 Cr 25 Mn 4 composition, identified from a Fe 75 Cr 20 Mn 5 starting point. The LLM autonomously adjusted its strategy in real time, demonstrating closed-loop decision-making using commodity hardware. This approach showcases the potential of LLMs as scientific co-pilots, capable of accelerating materials discovery and generalizable to other domains like biology and drug design.

Autonomy↗

DOE OSTI2025

Role of Uncertainty Quantification in the Explainability of Large Language Models for the Nuclear Industry

The meteoric rise of generative artificial intelligence (AI) large language models (LLMs) has created an opportunity to utilize them to increase efficiencies in a multitude of industries. While LLMs carry great potential to revolutionize the manner in which work is performed, numerous known deficiencies limit their utility, including the black box nature of the models, the stochastic nature of the response (i.e., presenting the same prompt multiple times results in different responses), and the potential for hallucination. Widespread adoption of LLMs in safety-critical industries such as nuclear will require some form of explainability to assure end users that the LLM’s response to a given query is valid. Model uncertainty is inherently linked to the concepts of trust and explainability, and can be used to identify situations in which the model is insufficiently certain about its answer. Although uncertainty is not enough in and of itself to determine the suitability of an answer—a model can be very certain of an inaccurate answer—it still provides valuable supporting information. Practical methodologies for gauging or quantifying the uncertainty in LLM outputs are presented herein, along with examples based on nuclear-specific prompts.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2025

Using Large Language Models to help customers monitor global threat data

Large Language Models have proven adept at answering general knowledge questions. To make these generative AI tools useful to our mission customers for monitoring global threats, the data sciences team at Sandia is utilizing retrieval augmented generation (RAG) techniques to customize these models with local data. The local data we use consists of data such as research articles and patent abstracts that we've collected over the last several years using automated pipelines.

Herzer, John Andrew [Sandia National Laboratories ↗

DOE OSTI2024

Improving Reliability of Large Language Models for Nuclear Power Plant Diagnostics Technical Presentation

Large Language Models (LLMs) struggle out of the box when answering factually about detailed questions, especially in domains that are sparsely represented in their training data. This causes hallucinations and reduces reliability making it difficult for them to be used in practice. This work shows that using RAG techniques can improve factual accuracy and reliability, allowing for the application of LLMs in specialized areas, even when those areas that aren’t extensively covered in their initial training.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2025

Connecting Minds: AI Use Cases to Bridge Power Systems and Large Language Models for Practical Applications

Recent advances in artificial intelligence (AI) and development of large language models (LLMs) present the opportunity to develop a new generation of power systems applications. In contrast with early power system AI applications based on structured numerical data, LLMs offer unique capabilities to perform logical reasoning using text documents, unstructured data, and application programming interface (API) calls to computational software. This paper seeks to bridge the knowledge gap between power systems engineers and LLM developers through a crosscutting explanation of use cases, characteristics, requirements, practical considerations from the perspectives of both LLM capabilities and industry needs. Specific focus is given to applications that can be realistically deployed by electric utilities. After introducing the architecture of LLMs and unique challenges of the power systems domain, this paper proposes twenty representative LLM applications grouped into categories of 1) power system operations, 2) asset management, 3) system planning and analytics, and 4) energy management and protection systems. Five use cases are presented within each category with descriptions of the motivation, objectives, approaches, example inputs / outputs, and benefits of each use case.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

Harnessing large language models’ zero-shot and few-shot learning capabilities for regulatory research

Abstract Large language models (LLMs) are sophisticated AI-driven models trained on vast sources of natural language data. They are adept at generating responses that closely mimic human conversational patterns. One of the most notable examples is OpenAI's ChatGPT, which has been extensively used across diverse sectors. Despite their flexibility, a significant challenge arises as most users must transmit their data to the servers of companies operating these models. Utilizing ChatGPT or similar models online may inadvertently expose sensitive information to the risk of data breaches. Therefore, implementing LLMs that are open source and smaller in scale within a secure local network becomes a crucial step for organizations where ensuring data privacy and protection has the highest priority, such as regulatory agencies. As a feasibility evaluation, we implemented a series of open-source LLMs within a regulatory agency’s local network and assessed their performance on specific tasks involving extracting relevant clinical pharmacology information from regulatory drug labels. Our research shows that some models work well in the context of few- or zero-shot learning, achieving performance comparable, or even better than, neural network models that needed thousands of training samples. One of the models was selected to address a real-world issue of finding intrinsic factors that affect drugs' clinical exposure without any training or fine-tuning. In a dataset of over 700 000 sentences, the model showed a 78.5% accuracy rate. Our work pointed to the possibility of implementing open-source LLMs within a secure local network and using these models to perform various natural language processing tasks when large numbers of training examples are unavailable.

Biochemistry & Molecular Biology↗

DOE OSTI2024

Large language model evaluation for high–performance computing software development

We apply AI-assisted large language model (LLM) capabilities of GPT-3 targeting high-performance computing (HPC) kernels for (i) code generation, and (ii) auto-parallelization of serial code in C ++, Fortran, Python and Julia. Our scope includes the following fundamental numerical kernels: AXPY, GEMV, GEMM, SpMV, Jacobi Stencil, and CG, and language/programming models: (1) C++ (e.g., OpenMP [including offload], OpenACC, Kokkos, SyCL, CUDA, and HIP), (2) Fortran (e.g., OpenMP [including offload] and OpenACC), (3) Python (e.g., numpy, Numba, cuPy, and pyCUDA), and (4) Julia (e.g., Threads, CUDA.jl, AMDGPU.jl, and KernelAbstractions.jl). Kernel implementations are generated using GitHub Copilot capabilities powered by the GPT-based OpenAI Codex available in Visual Studio Code given simple + + prompt variants. To quantify and compare the generated results, we propose a proficiency metric around the initial 10 suggestions given for each prompt. For auto-parallelization, we use ChatGPT interactively giving simple prompts as in a dialogue with another human including simple “prompt engineering” follow ups. Results suggest that correct outputs for C++ correlate with the adoption and maturity of programming models. For example, OpenMP and CUDA score really high, whereas HIP is still lacking. We found that prompts from either a targeted language such as Fortran or the more general-purpose Python can benefit from adding language keywords, while Julia prompts perform acceptably well for its Threads and CUDA.jl programming models. Finally, we expect to provide an initial quantifiable point of reference for code generation in each programming model using a state-of-the-art LLM. Overall, understanding the convergence of LLMs, AI, and HPC is crucial due to its rapidly evolving nature and how it is redefining human-computer interactions.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Large language models for transportation research: Methodologies, state of the art, and future opportunities

The rapid rise of large language models (LLMs) is transforming transportation research, with significant advancements emerging between 2023 and 2025, a period marked by the inception and swift growth of adopting and adapting LLMs for various transportation applications. Despite these significant advancements, however, a systematic review and synthesis of the existing literature remains lacking. This paper aims to fill this gap by providing a comprehensive review of the methodologies and applications of LLMs in transportation. We explore key applications, including autonomous driving, travel behavior prediction, and general transportation-related queries, alongside LLM methodologies such as zero- or few-shot learning, prompt engineering, and fine-tuning. From the review, critical research gaps are identified. From the methodological perspective, many of the research limitations can be addressed by integrating LLMs with existing tools and refining LLM architectures. From the application perspective, research opportunities for LLMs to address various transportation challenges are also explored. By synthesizing these findings, this review not only presents the state-of-the-art LLM adoption and adaptation in transportation, but also proposes future research directions as well as insights and recommendations for policymakers and practitioners, paving the way for greater LLM-driven research innovations in transportation in the future.

42 ENGINEERING↗

DOE OSTI2024

ChatGrid: Power Grid Visualization Empowered by Large Language Model

This paper presents a novel open framework, ChatGrid, for easy, intuitive, and interactive geospatial visualization of large-scale transmission networks. ChatGrid uses state-of-the-art techniques for geospatial visualization of large networks including 2.5D views, animated flows, hierarchical and level-based filtering, and aggregation to provide visual information in an easy, cognitive manner. The highlight of ChatGrid is a natural language query based interface powered by large language model (ChatGPT) that offers an enhanced interactive experience whereby the user asks a question and ChatGrid provides the information both in text and visual. We discuss the architecture, implementation, design decisions, and usage of large language model for ChatGrid.

Jin, Sichen↗

DOE OSTI2026

Scaling open-weight large language models for hydropower regulatory information extraction: A systematic analysis

Information extraction from regulatory and technical documents using large language models (LLMs) involves practical trade-offs between extraction quality and computational cost. We evaluate eight open-weight LLMs spanning 0.6B–70B parameters on hydropower licensing documents and report deployment-oriented evidence under a unified extraction schema and evaluation protocol. Across the model set, we observe clear scale-dependent trends in both baseline extraction quality and the effectiveness of reflective reasoning (self-checking) under our fixed-prompt, no-augmentation setting. Mid-scale models often provide a favorable balance of accuracy and efficiency, whereas the smallest models show limited or inconsistent gains from the reasoning variants tested. Larger models achieve the highest overall F1 scores but incur substantially greater compute and infrastructure requirements. We further find that reliability failure modes can distort conventional metrics in this domain: in particular, high recall can coincide with systematic extraction errors when models fabricate values for fields that are absent from the source text, underscoring the importance of conservative null handling and evidence-grounded evaluation. Overall, our study provides a reproducible resource–performance comparison for open-weight LLM-based extraction in hydropower regulatory documentation and offers practical guidance for model selection under different deployment constraints.

Evaluation protocol↗

DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Semantic schemas like Haystack 4, Brick and ASHRAE standard 223 enable the structured, standardized, and machine-readable representation of building data, facilitating interoperability, data integration, and advanced analytics. However, extracting information from these models requires specialized expertise in SPARQL and other programming languages, skills that are not commonly found among building professionals. Recent advancements in Large Language Models (LLMs), such as ChatGPT, enable the construction of queries using natural language, making it easier for individuals to interact with these systems in a manner that resembles everyday speech. However, these methods have not yet been tested on building semantic ontologies. This paper introduces a novel workflow and tool for enabling users to ask questions about a specific building's data, using natural language and receive answers automatically generated by GPT-4o. Our approach integrates semantic ontologies with advanced LLM capabilities to automate three critical steps: (1) generating SPARQL queries to retrieve time series references from ontological models, (2) extracting the corresponding time series data from the Building Automation System, and (3) performing computations and visualizations tailored to the user's query. The proposed method simplifies access to BAS data, allowing both domain experts and non-specialists to conduct sophisticated analyses without needing extensive technical knowledge of semantic web technologies. By demonstrating this pipeline, we facilitate more accessible and scalable data-driven decision-making in building operations and management.

Mulayim, Ozan Baris↗

DOE OSTI2025

Extraction and Analysis of Time Series Data from Building Automation Systems Using Large Language Models

Mulayim, Ozan Baris↗

NASA NTRS2025

A Preliminary Study on the Feasibility of Large Language Models for Detecting Micro-Behaviors Among Team Members in Space Missions

Large-language models (LLMs) have been recently used for spoken language understanding (SLU) to infer meaning and semantics from speech in tasks such as speaker intent and sentiment classification. Due to being trained on large amounts of data, and their ability to understand context and relationships between words, LLMs are competent, enabling them to generalize across tasks without requiring many task-specific training samples. This research examines the feasibility of few-shot learning in LLMs for detecting subtle, brief, and possibly unconscious interactions between team members, called ``micro-behaviors," and provides insights into the appropriate design of LLMs for this task. Our data came from 5 teams participating in a 45-day mission at the US National Aeronautics and Space Administration’s (NASA) Human Exploration Research Analog (HERA). More specifically we used data collected from team interaction battery (TIB) tasks teams performed five times in-mission which comprise an average 1.5 hours of conversation data per day. Micro-behaviors were coded according to an adapted version of Smith & Griffins (2022) theoretical framework in terms of Violation (i.e., presence of valenced behavior, uplifting/positive or discouraging/negative), Intensity (i.e., force of behavior in terms of how uplifting or discouraging is the behavior), and Intent (i.e., motive of the behavior in terms of whether it was deliberate or unintentional). We explore the ability of LLMs to detect the presence and intensity of micro-behaviors. We examine employing and fine-tuning readily available LLMs (i.e., RoBERTa, DistilBERT), as well as prompting state-of-the-art sequence classification models (i.e., Llama-2, Llama-3). In a total of 13,058 conversational turns (17.8% uplifting, 3.3% discouraging, 75.76% neutral, 3.14% nulls), we compute the macro F1-score of the 3-way micro-behavior classification task (i.e., classifying among uplifting, discouraging, and neutral; 33% chance). Results indicate that the RoBERTa model achieves a F1-score of 36.2% (uplift: 43.3% precision (P), 15.1% recall (R); discourage: 20% P, 0.5% R). These results significantly improve when we augment the data via paraphrasing in the RoBERTa model, reaching a 41.2% macro F1-score (uplift: 37.7% P, 86.3% R; discourage: 3.5% P, 1.8% R). Finally, the Llama-2 model with 3-shot prompting yields 38% macro F1-score (uplift: 28.7% P, 20% R; discourage: 7.2% P, 18% R), which is slightly better compared to the RoBERTa model without data augmentation, highlighting the effectiveness of sequence classification models in detecting minority classes with a small sample size. Findings indicate that LLMs hold potential to detect subtle behaviors in conversations, which could be valuable in assessing team behavior in space exploration missions. Future studies will evaluate the performance of different LLM prompting strategies or fine-tuning methods.

Ankush Raut↗