Search NASA⌕ Search

SEARCH · Search NASA

Results for “language”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Large Language Model for Validation, Optical Calibration, and Learning (VOCAL) Distributed Temperature Sensing Interface

Distributed temperature sensing (DTS) using fiber optic sensors (FOS) offers a promising method for temperature measurements in advanced reactors, such as sodium fast reactors and molten salt cooled reactors. To support the calibration and validation of DTS measurements, Argonne National Laboratory developed the Validation, Optical Calibration, and Learning (VOCAL) software package. This report describes the integration of a local large language model (LLM) with a retrieval-augmented generation (RAG) system into the VOCAL interface to serve as an interactive user assistant. The LLM framework enhances the VOCAL platform’s accessibility to users by explaining interface components, clarifying inputs and outputs, and answering user queries dynamically in real-time. The accuracy of the LLM assistant performance was evaluated with 20 queries regarding the interface and its parameters using experimental data from the Thermal Hydraulic Experimental Test Article (THETA) facility. Results demonstrate that the LLM achieved a 95% accuracy rate, with a BERTScore of 0.8816 and SBERT value of 0.7417. Furthermore, validation of the RAG system within the LLM framework showed optimal accuracy with k-values between 1 and 2 using the k-refinement convergence test. The prompt perturbation analysis demonstrated good initial consistency for the RAG system, exhibiting the highest accuracy under punctuation variations and the greatest sensitivity under query reordering. Notably, the model’s errors were limited to data retrieval failures rather than factual hallucinations, reinforcing its baseline reliability. The integration of LLM provides a highly accurate, userfriendly enhancement to the VOCAL platform without disrupting its core computational capabilities for FOS calibration and validation.

Hong, Evan↗
DOE OSTI2024

Optimizing Distributed Training on Frontier for Large Language Models

Large language models (LLMs) have demonstrated remarkable success as foundational models, benefiting various downstream applications through fine-tuning. Loss scaling studies have demonstrated the superior performance of larger LLMs compared to their smaller counterparts. Nevertheless, training LLMs with billions of parameters poses significant challenges and requires considerable computational resources. For example, training a one trillion parameter GPT-style model on 20 trillion tokens requires a staggering 120 million exaflops. This research explores efficient distributed training strategies to extract this computation from Frontier, the world's first exascale supercomputer. We enable and investigate various model and data parallel training techniques, such as tensor parallelism, pipeline parallelism, and sharded data parallelism, to facilitate training a trillion-parameter model on Frontier. We empirically assess these techniques and their associated parameters to determine their impact on memory footprint, communication latency, and GPU's computational efficiency. We analyze the complex interplay among these techniques and find a strategy to combine them to achieve high throughput through hyperparameter tuning. We have identified efficient strategies for training large LLMs of varying sizes through empirical analysis and hyperparameter tuning. For 22 Billion, 175 Billion, and 1 Trillion parameters, we achieved GPU throughputs of 38.38%, 36.14%, and 31.96%, respectively. For the training of the 175 Billion parameter model and the 1 Trillion parameter model, we achieved 100% weak scaling efficiency on 1024 and 3072 Mi250X GPUs, respectively. We also achieved strong scaling efficiencies of 89% and 87% for these two models. We trained these models only tens of iterations instead of training till completion.

Yin, Junqi↗
DOE OSTI2024

Implementing Ordinary Differential Equation Solvers in Rust Programming Language for Modeling Vehicle Powertrain Systems: Preprint

Efficient and accurate ordinary differential equation (ODE) solvers are necessary for powertrain and vehicle dynamics modeling. However, current commercial ODE solvers can be financially prohibitive, leading to a need for accessible, effective, open-source ODE solvers designed for powertrain modeling. Rust is a compiled programming language that has the potential to be used for fast and easy-to-use powertrain models, given its exceptional computational performance, robust package ecosystem, and short time required for modelers to become proficient. However, of the three commonly used (>3,000 downloads) packages in Rust with ODE solver capabilities, only one has more than four numerical methods implemented, and none are designed specifically for modeling physical systems. Therefore, the goal of the Differential Equation System Solver (DESS) was to implement accurate ODE solvers in Rust designed for the component-based problems often seen in powertrain modeling. DESS is a text-based software package that provides a flexible framework for building and solving systems of ODEs. This allows DESS to be included as a dependency for automotive powertrain models that require a variety of solvers and solver configurations. Seven explicit ODE solver methods have been implemented in DESS: Euler’s, Heun’s, midpoint, Ralston’s, classic Runge-Kutta, Bogacki-Shampine, and Cash-Karp. These represent five fixed-step methods and two adaptive-step methods. This paper shows that the solver implementations increase accuracy and computational efficiency compared to Euler's method when modeling a system of three thermal masses in Rust. DESS also includes features designed for modeling component-based physical systems. Users can define relationships between nodes in their system, which the package then translates into a system of equations, leading to simpler and more intuitive code. In the case of a three-thermal-mass system, the user can specify node thermal properties (e.g., thermal capacitance), how nodes are interconnected, and thermal conductance between nodes rather than providing a system of equations. The core contribution from this work is an open-source, text-based Rust package with ODE solvers for automotive powertrain modeling to support cost-free, fast, and accurate simulation.

ADVANCED PROPULSION SYSTEMS↗
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 OSTI2024

Evaluating the Use of Foundational Chemical Language Models in Multimodal Graph Fusion

Rapid and accurate prediction of the physicochemical properties of molecules given their structures remains a key challenge in cheminformatics. Machine learning approaches offer high-throughput options, but the optimality of inductive biases and data representations are up for debate. For example, BERT-based masked language models (MLMs) can be trained in a self-supervised way on hundreds of millions to billions of readily available SMILES strings. Another option is graph neural networks (GNNs), which can operate directly on molecular structures. Yet, generating accurate molecular geometry is computationally expensive, leading to a relative scarcity in data compared to SMILES strings. It is attractive to combine these two paradigms by pre-training an LM on a large corpus of SMILES strings and embedding these representation into a geometric graph neural network. Despite the promise of such an approach, and contrary to previous studies, we find mixed results with the combination of the LMs and GNNs on several molecule datasets. In particular, we found evidence for improvement on the FreeSolv and QM7 benchmarks, but degraded performance on the ESOL, LIPO and QM9 datasets compared to a GNN baseline.

Francel, Collin [University of Alabama]↗
DOE OSTI2024

VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images

Images are increasingly becoming the currency for documenting biodiversity on the planet, providing novel opportunities for accelerating scientific discoveries in the field of organismal biology, especially with the advent of large vision-language models (VLMs). We ask if pre-trained VLMs can aid scientists in answering a range of biologically relevant questions without any additional fine-tuning. In this paper, we evaluate the effectiveness of 12 state-of-the-art (SOTA) VLMs in the field of organismal biology using a novel dataset, VLM4Bio, consisting of 469K question8 answer pairs involving 30K images from three groups of organisms: fishes, birds, and butterflies, covering five biologically relevant tasks. We also explore the effects of applying prompting techniques and tests for reasoning hallucination on the performance of VLMs, shedding new light on the capabilities of current SOTA VLMs in answering biologically relevant questions using images

Maruf, M [Virginia Tech, Blacksburg]↗
DOE OSTI2025

Automating and Evaluating Large Language Models for Accurate Text Summarization Under Zero-Shot Conditions

Automated text summarization (ATS) is crucial for collecting specialized, domain-specific information. Zero-shot learning (ZSL) allows large language models (LLMs) to respond to prompts on information not included in their training, playing a vital role in this process. This study evaluates LLMs' effectiveness in generating accurate summaries under ZSL conditions and explores using retrieval augmented generation (RAG) and prompt engineering to enhance factual accuracy and understanding. We combined LLMs with summarization modeling, prompt engineering, and RAG, evaluating the summaries using the METEOR metric and keyword frequencies through word clouds. Results indicate that LLMs are generally well-suited for ATS tasks, demonstrating an ability to handle specialized information under ZSL conditions with RAG. However, web scraping limitations hinder a single generalized retrieval mechanism. While LLMs show promise for ATS under ZSL conditions with RAG, challenges like goal misgeneralization and web scraping limitations need addressing. Future research should focus on solutions to these issues.

Priebe Mendes Rocha, Maria Eduarda [ORNL]↗
DOE OSTI2025

Can Large Language Models Understand Intermediate Representations?

Intermediate Representations (IRs) are essential in compiler design and program analysis, yet their comprehension by Large Language Models (LLMs) remains underexplored. This paper presents a pioneering empirical study to investigate the capabilities of LLMs, including GPT-4, GPT-3, Gemma 2, LLaMA 3.1, and Code Llama, in understanding IRs. We analyze their performance across four tasks: Control Flow Graph (CFG) reconstruction, decompilation, code summarization, and execution reasoning. Our results indicate that while LLMs demonstrate competence in parsing IR syntax and recognizing high-level structures, they struggle with control flow reasoning, execution semantics, and loop handling. Specifically, they often misinterpret branching instructions, omit critical IR operations, and rely on heuristic-based reasoning, leading to errors in CFG reconstruction, IR decompilation, and execution reasoning. The study underscores the necessity for IR-specific enhancements in LLMs, recommending fine-tuning on structured IR datasets and integration of explicit control flow models to augment their comprehension and handling of IR-related tasks.

Jiang, Hailong↗
DOE OSTI2026

QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding

Quantum computing calibration depends on interpreting experimental data, and calibration plots provide the most universal human-readable representation for this task, yet no systematic evaluation exists of how well vision-language models (VLMs) interpret them. We introduce QCalEval, the first VLM benchmark for quantum calibration plots: 243 samples across 87 scenario types from 22 experiment families, spanning superconducting qubits and neutral atoms, evaluated on six question types in both zero-shot and in-context learning settings. The best general-purpose zero-shot model reaches a mean score of 72.3, and many open-weight models degrade under multi-image in-context learning, whereas frontier closed models improve substantially. A supervised fine-tuning ablation at the 9-billion-parameter scale shows that SFT improves zero-shot performance but cannot close the multimodal in-context learning gap. As a reference case study, we release NVIDIA Ising Calibration 1, an open-weight model based on Qwen3.5-35B-A3B that reaches 74.7 zero-shot average score.

Cao, Shuxiang↗
DOE OSTI2026

CTRL-STEER: Closed-Loop Neuron Activation Control in Vision-Language-Action Models

Vision-Language-Action (VLA) models enable test-time behavioral steering via neuron-level interventions, but existing methods use fixed strengths and operate in open loop. This static modulation fails under evolving task dynamics, leading to overcorrection, oscillations, and reduced task success—especially for temporal attributes like speed. We propose CTRL-STEER, a control-theoretic framework that casts activation steering as closed-loop feedback with adaptive, time-varying interventions. Instead of assuming neurons encode temporal concepts, we steer along motion-aligned residual directions and regulate intervention magnitude via feedback. We instantiate this with both PID and reinforcement learning controllers that jointly optimize concept adherence and task success. Experiments on fine-tuned OpenVLA policies across four LIBERO suites show improved stability and a better steering–success trade-off over fixed-coefficient baselines, without retraining the base model.

Babu, Abhijith [Florida International University, ↗
DOE OSTI2024

Designing complex concentrated alloys with quantum machine learning and language modeling

Designing novel complex concentrated alloys (CCAs) is an essential topic in materials science. However, due to the complicated high-dimensional component-property relationship, tuning material properties by researchers’ experience is challenging, even when guided by physical or empirical rules. Here, we adopt quantum computing (QC) technology and machine learning models to provide a proof-of-concept application of QC in physical metallurgy. We propose a quantum support vector machine (QSVM) model to predict single-phase CCAs. We show that fine-tuned quantum kernels with entanglement deliver promising performance, with a maximum accuracy of 89.4%. The QSVM model is then used to identify 1,741 lightweight CCAs jointly with a new text-mining-based method. Meanwhile, we devise a controllable approach to study the effect of noise on model performance and find that the noise level needs to be minimized for high-performance QSVM models. Finally, this study provides a practical and general approach to designing CCAs based on quantum technologies.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Evolving language of pediatric anxiety in electronic health records

Objectives This study aimed to identify and quantify semantic drift (ie, the change in semantic meaning over time) within expert-defined anxiety-related (AR) terminology and compare it to common electronic health record (EHR) vocabulary across longitudinal pediatric clinical notes. Materials and Methods A corpus of pediatric clinical notes from 2009 to 2022 was analyzed using computational methods. Semantic drift for each term was quantified using cosine similarity between annual temporal word embeddings. Contextual meaning was examined through changes in nearest neighbors across years. The Laws of Semantic Change were applied to assess the influence of word frequency and polysemy. Vocabulary terms were categorized as AR or common EHR. Results 98% of AR terminology maintained a cosine similarity between 0.00 and 0.50, indicating moderate semantic stability, whereas 90% of common EHR terms remained between 0.00 and 0.25, showing greater contextual stability overall. Frequent terms exhibited minimal change (Frequency Coefficient = 0.04), whereas highly polysemous or abbreviated terms showed less stability (Polysemy Coefficient = 0.630). AR terminology drifted more slowly than general EHR vocabulary (Type Coefficient = −0.179), further supported by significant year–type interactions (Coef = −0.09 to −0.523). Discussion Although anxiety-related terminology demonstrates slower semantic drift than general EHR vocabulary, subtle contextual shifts still occur that may affect downstream interpretability and retrieval in automated systems. Conclusion Continuous linguistic monitoring and adaptive modeling are essential to maintain semantic fidelity and ensure the long-term reliability of clinical decision support systems as healthcare documentation evolves.

Pediatric anxiety disorders↗
DOE OSTI2024

Root Cause Correlation Analysis of Software Failures via Orthogonal Defect Classification and Natural Language Processing

Systems theoretic process analysis (STPA) is becoming an increasingly popular technique to assess how complex digital software systems can fail. Rather than defining failures by their observable failure events, which may be sparse especially for safety rated nuclear digital instrumentation and control systems (DI&C), failures are defined as postulated unsafe actions under specific contextual conditions. This permits a top-down analysis of system hazards and identifies whether imposed constraints and requirements can sufficiently address undesirable hazards. However, STPA is a qualitative approach at identifying inadequacies in the development process and cannot currently be used to quantify unsafe action likelihoods for probabilistic risk assessment. Therefore, in this work, we examine the root causes of software failure and explore whether a consistent correlation can be linked to specific unsafe action classes. We implement Lbl2Vec, an unsupervised document classification and retrieval algorithm, on a database of 4,096 software defect reports acquired from various open-source software systems. By analyzing sentence structure, embedded labels, and word vectors, we show that certain defect types positively correlate to specific unsafe action classes over others. The correlations developed can be used to estimate the failure probability of safety intended DI&C systems which provides a licensing basis for nuclear plant modernization efforts.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Root Cause Correlation Analysis of Software Failures via Orthogonal Defect Classification and Natural Language Processing

Systems theoretic process analysis (STPA) is becoming an increasingly popular technique to assess how complex digital software systems can fail. Rather than defining failures by their observable failure events, which may be sparse especially for safety rated nuclear digital instrumentation and control systems (DI&C), failures are defined as postulated unsafe actions under specific contextual conditions. This permits a top-down analysis of system hazards and identifies whether imposed constraints and requirements can sufficiently address undesirable hazards. However, STPA is a qualitative approach at identifying inadequacies in the development process and cannot currently be used to quantify unsafe action likelihoods for probabilistic risk assessment. Therefore, in this work, we examine the root causes of software failure and explore whether a consistent correlation can be linked to specific unsafe action classes. We implement Lbl2Vec, an unsupervised document classification and retrieval algorithm, on a database of 4,096 software defect reports acquired from various open-source software systems. By analyzing sentence structure, embedded labels, and word vectors, we show that certain defect types positively correlate to specific unsafe action classes over others. The correlations developed can be used to estimate the failure probability of safety intended DI&C systems which provides a licensing basis for nuclear plant modernization efforts.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗