Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “language models”

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

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

At least 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
NASA NTRS2003

Targeted Help for Spoken Dialogue Systems: Intelligent Feedback Improves Naive Users' Performance

We present experimental evidence that providing naive users of a spoken dialogue system with immediate help messages related to their out-of-coverage utterances improves their success in using the system. A grammar-based recognizer and a Statistical Language Model (SLM) recognizer are run simultaneously. If the grammar-based recognizer suceeds, the less accurate SLM recognizer hypothesis is not used. When the grammar-based recognizer fails and the SLM recognizer produces a recognition hypothesis, this result is used by the Targeted Help agent to give the user feed-back on what was recognized, a diagnosis of what was problematic about the utterance, and a related in-coverage example. The in-coverage example is intended to encourage alignment between user inputs and the language model of the system. We report on controlled experiments on a spoken dialogue system for command and control of a simulated robotic helicopter.

Hockey, Beth Ann↗
DOE OSTI2025

Agentic AI vs ML-Based Autotuning: A Comparative Study for Loop Reordering Optimization

High Performance Computing (HPC) applications rely heavily on code optimizations to achieve good performance on modern CPU and GPU architectures. Traditional Machine Learning auto-tuning approaches have demonstrated success in exploring high-dimensional spaces, but they often require expensive compile-run evaluations and lack adaptability for large HPC applications. The recent advances in Large Language Models (LLMs) and Agentic AI systems raise intriguing questions about the potential of these approaches to address specific optimization methodologies. This work aims to answer an essential question for the HPC community: “How Agentic AI Systems Compare to Traditional ML Autotuning Techniques?” To address this question, we present a comparative analysis between a traditional ML-based optimization approach and an Agentic AI system, evaluating their respective capabilities and limitations for loop-level optimization. In addition, we introduced a new Agentic AI system named LoopGen-AI using three different Large Language Models: GPT-4.1, Claude 4.0, and Gemini 2.5. A key finding is that LoopGen-AI achieves competitive per-formance with only a few program runs, the reasoning logs from the agents revealed that their decisions rely heavily on the combination of semantic understanding of the target kernel with dynamic feedback from the environment, highlighting a promising new dimension in performance tuning. In contrast, ML-based autotuners focus on statistical exploration, and require orders of magnitude more runs to reach peak performance. Additionally, our analysis shows that prompt engineering, particularly using Persona + Context Manager patterns, significantly impacts the effectiveness of Agentic AI. Our results indicate that while Agentic AI systems are not yet a complete replacement for ML-based autotuners, it can effectively complement traditional methods.

Rosas, Miguel Romero↗
DOE OSTI2026

From natural language to control signals: a conceptual framework for semantic channel finding in complex experimental infrastructure

Modern experimental platforms such as particle accelerators, fusion devices, telescopes, and industrial process control systems expose tens to hundreds of thousands of control and diagnostic channels, accumulated over decades of hardware evolution. Operators and AI systems alike depend on informal expert knowledge, inconsistent naming conventions, and scattered documentation to locate the signals required for monitoring, troubleshooting, and automated control, creating a persistent bottleneck for reliability, scalability, and emerging language-model-driven interfaces. We formalize semantic channel finding, the task of mapping natural-language intent to concrete control-system signals, as a general problem in complex experimental infrastructure, and introduce a four-paradigm conceptual framework to guide architecture selection based on facility-specific data regimes. The paradigms span (i) direct in-context lookup over small, curated channel dictionaries, (ii) constrained hierarchical navigation through structured trees, (iii) interactive agent exploration using iterative reasoning and tool-based database queries, and (iv) ontology-grounded semantic search that decouples channel meaning from facility-specific naming conventions. We demonstrate the practical feasibility of each paradigm through proof-of-concept implementations at four operational facilities spanning two orders of magnitude in scale: from compact free-electron lasers to large synchrotron light sources, operating under diverse control-system architectures ranging from clean hierarchical naming schemes to legacy environments with decades of heterogeneous conventions. Where evaluated against expert-curated operational queries, these instantiations achieve 90%–97% accuracy, validating the framework’s applicability across real-world deployment scenarios. To accelerate adoption across the broader scientific and industrial control-system community, we release open-source, plug-and-play implementations of all three interactive paradigms-direct lookup, hierarchical navigation, and middle-layer exploration-within the Osprey framework, together with tools for channel database generation, interactive testing, and minimal-configuration deployment. This work establishes semantic channel finding as a foundational capability for human-centric and agentic AI interfaces at large-scale facilities, providing both a systematic framework for architecture design and practical resources to enable adoption without building custom infrastructure from scratch.

channel finding↗
NASA NTRS1998

Modeling Controller Tasks for Safety Analysis

As control systems become more complex, the use of automated control has increased. At the same time, the role of the human operator has changed from primary system controller to supervisor or monitor. Safe design of the human computer interaction becomes more difficult. In this paper, we present a visual task modeling language that can be used by system designers to model human-computer interactions. The visual models can be translated into SpecTRM-RL, a blackbox specification language for modeling the automated portion of the control system. The SpecTRM-RL suite of analysis tools allow the designer to perform formal and informal safety analyses on the task model in isolation or integrated with the rest of the modeled system.

Brown, Molly↗
DOE OSTI2022

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↗
NASA NTRS1979

SAINT: A combined simulation language for modeling man-machine systems

SAINT (Systems Analysis of Integrated Networks of Tasks) is a network modeling and simulation technique for design and analysis of complex man machine systems. SAINT provides the conceptual framework for representing systems that consist of discrete task elements, continuous state variables, and interactions between them. It also provides a mechanism for combining human performance models and dynamic system behaviors in a single modeling structure. The SAINT technique is described and applications of the SAINT are discussed.

Seifert, D. J.↗
NASA NTRS1988

Development of automation and robotics for space via computer graphic simulation methods

A robot simulation system, has been developed to perform automation and robotics system design studies. The system uses a procedure-oriented solid modeling language to produce a model of the robotic mechanism. The simulator generates the kinematics, inverse kinematics, dynamics, control, and real-time graphic simulations needed to evaluate the performance of the model. Simulation examples are presented, including simulation of the Space Station and the design of telerobotics for the Orbital Maneuvering Vehicle.

Fernandez, Ken↗
NASA NTRS2012

Modeling Off-Nominal Behavior in SysML

Specification and development of fault management functionality in systems is performed in an ad hoc way - more of an art than a science. Improvements to system reliability, availability, safety and resilience will be limited without infusion of additional formality into the practice of fault management. Key to the formalization of fault management is a precise representation of off-nominal behavior. Using the upcoming Soil Moisture Active-Passive (SMAP) mission for source material, we have modeled the off-nominal behavior of the SMAP system during its initial spin-up activity, using the System Modeling Language (SysML). In the course of developing these models, we have developed generic patterns for capturing off-nominal behavior in SysML. We show how these patterns provide useful ways of reasoning about the system (e.g., checking for completeness and effectiveness) and allow the automatic generation of typical artifacts (e.g., success trees and FMECAs) used in system analyses.

fault protection↗
NASA NTRS2021

Programming - What is Next?

The paper provides an introduction to the track: “Program- ming - What is Next?”, organized by the authors as part of ISoLA 2021: the 9th International Symposium On Leveraging Applications of Formal Methods, Verification and Validation. A total of 14 papers were pre- sented in the track, with responses to the question: what are the trends in current more recent programming languages, and what can be expected of future languages?. The track covers such topics as general-purpose programming languages, domain-specific languages, formal methods and modeling languages, textual versus graphical languages, and application programming versus embedded programming.

Steffen, Bernhard↗
NASA NTRS2024

Artificial Intelligence Workshop Report

The 4th NASA Science Mission Directorate (SMD) Artificial Intelligence (AI) Workshop, held during March 25-27, 2024, in Huntsville, AL, highlighted the significant potential of AI and machine learning (ML) in scientific research and processes. The workshop, supported by the NASA Office of Chief Science Data Officer (OCSDO), emphasized the critical role of foundation models (FMs) and large language models (LLMs) in advancing scientific disciplines. The event brought together domain scientists, computer scientists, AI experts, program managers, program scientists, and industry partners to address key challenges and explore opportunities in applying these advanced technologies.

Manil Maskey↗
NASA NTRS2013

Domain-Specific Languages and Diagram Customization for a Concurrent Engineering Environment

A major open question for advocates of Model-Based Systems Engineering (MBSE) is the question of how system and subsystem engineers will work together. The Systems Modeling Language (SysML), like any language intended for a large audience, is in tension between the desires for simplicity and for expressiveness. In order to be more expressive, many specialized language elements may be introduced, which will unfortunately make a complete understanding of the language a more daunting task. While this may be acceptable for systems modelers, it will increase the challenge of including subsystem engineers in the modeling effort. One possible answer to this situation is the use of Domain-Specific Languages (DSL), which are fully supported by the Unified Modeling Language (UML). SysML is in fact a DSL for systems engineering. The expressive power of a DSL can be enhanced through the use of diagram customization. Various domains have already developed their own schematic vocabularies. Within the space engineering community, two excellent examples are the propulsion and telecommunication subsystems. A return to simple box-and-line diagrams (e.g., the SysML Internal Block Diagram) are in many ways a step backward. In order allow subsystem engineers to contribute directly to the model, it is necessary to make a system modeling tool at least approximate in accessibility to drawing tools like Microsoft PowerPoint and Visio. The challenge is made more extreme in a concurrent engineering environment, where designs must often be drafted in an hour or two. In the case of the Jet Propulsion Laboratory's Team X concurrent design team, a subsystem is specified using a combination of PowerPoint for drawing and Excel for calculation. A pilot has been undertaken in order to meld the drawing portion and the production of master equipment lists (MELs) via a SysML authoring tool, MagicDraw. Team X currently interacts with its customers in a process of sharing presentations. There are several inefficiencies that arise from this situation. The first is that a customer team must wait two weeks to a month (which is 2-4 times the duration of most Team X studies themselves) for a finalized, detailed design description. Another is that this information must be re-entered by hand into the set of engineering artifacts and design tools that the mission concept team uses after a study is complete. Further, there is no persistent connection to Team X or institutionally shared formulation design tools and data after a given study, again reducing the direct reuse of designs created in a Team X study. This paper presents the underpinnings of subsystem DSLs as they were developed for this pilot. This includes specialized semantics for different domains as well as the process by which major categories of objects were derived in support of defining the DSLs. The feedback given to us by the domain experts on usability, along with a pilot study with the partial inclusion of these tools is also discussed.

Cole, Bjorn↗
NASA NTRS2011

Model-Based Systems Engineering for Capturing Mission Architecture System Processes with an Application Case Study - Orion Flight Test 1

Model-based Systems Engineering (MBSE) is an emerging methodology that can be leveraged to enhance many system development processes. MBSE allows for the centralization of an architecture description that would otherwise be stored in various locations and formats, thus simplifying communication among the project stakeholders, inducing commonality in representation, and expediting report generation. This paper outlines the MBSE approach taken to capture the processes of two different, but related, architectures by employing the Systems Modeling Language (SysML) as a standard for architecture description and the modeling tool MagicDraw. The overarching goal of this study was to demonstrate the effectiveness of MBSE as a means of capturing and designing a mission systems architecture. The first portion of the project focused on capturing the necessary system engineering activities that occur when designing, developing, and deploying a mission systems architecture for a space mission. The second part applies activities from the first to an application problem - the system engineering of the Orion Flight Test 1 (OFT-1) End-to-End Information System (EEIS). By modeling the activities required to create a space mission architecture and then implementing those activities in an application problem, the utility of MBSE as an approach to systems engineering can be demonstrated.

Orion Flight Test 1 (OFT-1)↗
DOE OSTI2025

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↗
DOE OSTI2024

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↗
DOE OSTI2025

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↗
DOE OSTI2025

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↗
DOE OSTI2025

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↗