Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Large Language Models (LLMs)”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Dual Context: Leveraging Structured Application Context for Code Generation and Runtime Feature Activation via Chat Interfaces

Integrating artificial intelligence (AI) capabilities into software applications typically involves two common paths. For developers, AI assists in generating and documenting source code and other related software engineering efforts. For users, AI assists them through question-and-answer exchanges via chatbots. Both approaches have their value, but neither effectively leverages the modularity of component-based architectures that modern web application frameworks offer. We implement a proof of concept within a centralized suite of applications used for the Atmospheric Radiation Measurement (ARM) Data Center Operational Tools, where we introduce a third integration path through the ARM Context Engine (ACE). ACE is a context driven system that uses structured contextual specifications to enable Large Language Models (LLMs) to render interactive and feature-rich user interface (UI) components directly within chat responses, alongside or in place of conventional text outputs. These specifications serve two important purposes across what we call code context and UI context. Code context provides AI-assisted development tools with structured application knowledge beyond raw code, including component relationships, architectural patterns and schematic information, enabling the generation of consistent, well-structured code. UI context defines the rules for enabling and rendering component features at runtime based on the user's natural language input, allowing end users to activate capabilities such as data export, filtering, and pagination within chat responses, without requiring code changes or redeployment. We demonstrate, through a comparative evaluation against general-purpose AI chatbots, that context-driven component rendering provides interactive capabilities that text-based responses cannot replicate, including deterministic component behavior, application-consistent design language, and on-demand feature activation. A development effort comparison further shows that features that traditionally require multi-step development cycles can be activated with a single naturallanguage request. In this ongoing work, we present ACE as an emerging approach to AI integration that positions modular, well-documented software architecture as the foundation for AI-ready applications. ACE treats context as a shared resource across both development and user-facing AI, bringing cohesion to conventionally disconnected efforts, bridging developer tooling and end-user capabilities within a single framework.

Tadimeti, Vijay [ORNL]↗
DOE OSTI2026

Cooling Matters: Benchmarking Large Language Models and Vision-Language Models on Liquid-Cooled Versus Air-Cooled H100 GPU Systems

The unprecedented growth in artificial intelligence (AI) workloads, recently dominated by large language models (LLMs) and vision-language models (VLMs), has intensified power and cooling demands in data centers. This study benchmarks LLMs and VLMs on two HGX nodes, each with 8× NVIDIA H100 graphics processing units (GPUs), using liquid and air cooling. Leveraging GPU Burn, Weights & Biases, and IPMItool, we collect detailed thermal, power, and computation data. Results show that the liquid-cooled systems maintain GPU temperatures between 41-50$^\circ$C, while the air-cooled counterparts fluctuate between 54-72$^\circ$C under load. This thermal stability of liquid-cooled systems yields 17% higher performance (54 TFLOPs/ GPU vs. 46 TFLOPs/GPU), performance-per-watt, reduced energy overhead, and greater system efficiency than the air-cooled counterparts. These findings underscore the energy and sustainability benefits of liquid cooling, offering a compelling path forward for hyperscale data centers seeking to optimize AI infrastructure. https://github.com/iscaas/Cooling-Matters.

Latif, Imran↗
DOE OSTI2025

Benchmarking large language models for materials synthesis: The case of atomic layer deposition

In this work, we introduce an open-ended question benchmark, ALDbench, to evaluate the performance of large language models (LLMs) in materials synthesis, and, in particular, in the field of atomic layer deposition, a thin film growth technique used in energy applications and microelectronics. Our benchmark comprises questions with a level of difficulty ranging from the graduate level to domain expert current with the state of the art in the field. Human experts reviewed the questions along the criteria of difficulty and specificity, and the model responses along four different criteria: overall quality, specificity, relevance, and accuracy. We ran this benchmark on an instance of OpenAI’s GPT-4o. The responses from the model received a composite quality score of 3.7 on a 1–5 scale, consistent with a passing grade. However, 36% of the questions received at least one below average score. An in-depth analysis of the responses identified at least five instances of suspected hallucination. Finally, we observed statistically significant correlations between the difficulty of the question and the quality of the response, the difficulty of the question and the relevance of the response, the specificity of the question, and the accuracy of the response as graded by the human experts. Furthermore, this emphasizes the need to evaluate LLMs across multiple criteria beyond difficulty or accuracy.

Artificial intelligence↗
DOE OSTI2023

FORGE: Pre-Training Open Foundation Models for Science

Large language models (LLMs) are poised to revolutionize the way we conduct scientific research. However, both model complexity and pre-training cost are impeding effective adoption for the wider science community. Identifying suitable scientific use cases, finding the optimal balance between model and data sizes, and scaling up model training are among the most pressing issues that need to be addressed. In this study, we provide practical solutions for building and using LLM-based foundation models targeting scientific research use cases. We present an end-to-end examination of the effectiveness of LLMs in scientific research, including their scaling behavior and computational requirements on Frontier, the first Exascale supercomputer. We have also developed for release to the scientific community a suite of open foundation models called FORGE with up to 26B parameters using 257B tokens from over 200M scientific articles, with performance either on par or superior to other state-of-the-art comparable models. We have demonstrated the use and effectiveness of FORGE on scientific downstream tasks. Our research establishes best practices that can be applied across various fields to take advantage of LLMs for scientific discovery.

Yin, Junqi↗
DOE OSTI2024

Large Language Models for the Creation and Use of Semantic Ontologies in Buildings: Requirements and Challenges

Semantic ontologies offer a formalized, machine-readable framework for representing knowledge, enabling the structured description of complex systems. In the building domain, the adoption of ontologies like the Brick schema has transformed how buildings and their systems are modeled by providing a standardized, interoperable language. However, the complexity and the steep learning curve involved in developing and querying semantic models present substantial challenges, often requiring a workforce with specialized expertise. This paper builds on our experience in investigating how Large Language Models (LLMs) can help address these challenges, focusing on their role in constructing and querying of semantic models, particularly using the Brick Schema. Our study outlines the requirements and metrics for evaluating the scalability and effectiveness of LLM-based tools, while also discussing the current challenges and limitations in developing such tools. Ultimately, this paper aims to orient research efforts as various groups experiment with diverse techniques, while enabling more effective comparison of emerging solutions and fostering collaboration across the field.

Mulayim, Ozan Baris↗
DOE OSTI2025

ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training

Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention mechanism, which is a critical component of transformer-based LLMs. In this paper, we investigate the impact of faults on LLM training, focusing on INF, NaN, and near-INF values in the computation results with systematic fault injection experiments. We observe the propagation patterns of these errors, which can trigger non-trainable states in the model and disrupt training, forcing the procedure to load from checkpoints. To mitigate the impact of these faults, we propose ATTNChecker, the first Algorithm-Based Fault Tolerance (ABFT) technique tailored for the attention mechanism in LLMs. ATTNChecker is designed based on fault propagation patterns of LLM and incorporates performance optimization to adapt to both system reliability and model vulnerability while providing lightweight protection for fast LLM training. Evaluations on four LLMs show that ATTNChecker on average incurs on average 7% overhead on training while detecting and correcting all extreme errors. Compared with the state-of-the-art checkpoint/restore approach, ATTNChecker reduces recovery overhead by up to 49×.

Liang, Yuhang [University of Alabama - Birmingham]↗
DOE OSTI2025

AI-Powered Knowledge Graphs for Neuromorphic and Energy-Efficient Computing

The surge in scientific literature obscures breakthroughs and hinders the discovery of new research paths. We propose an artificial intelligence (AI) powered framework using large language models (LLMs) and knowledge graphs (KGs) to automate parts of scientific discovery, focusing on energy-efficient AI circuits. Our hybrid approach combines LLMs, structured data, and ontology-based reasoning to construct a comprehensive knowledge graph that integrates insights across computational neuroscience, spiking neuron models, learning rules, architectural motifs, and neuromorphic device technologies. This multi-domain representation enables the generation of hypotheses that connect biological function with implementable, energy-efficient hardware architectures. Using KG embeddings and graph neural networks, the framework generates hypotheses for novel circuits, validates them through optimization on exascale HPC systems, and with tools like SuperNeuro and Fugu, the most promising designs will be prototyped in hardware. This open-source system aims to accelerate discoveries and bridging neuroscience with hardware innovation, drive collaboration, and unlock new opportunities in low-power AI computing.

Gautam, Ashish [ORNL]↗
DOE OSTI2025

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.

Wang, Jiayi [ORNL]↗
DOE OSTI2025

BuildingQA: A Benchmark for Natural Language Question Answering over Building Knowledge Graphs

Graph-based representations of building metadata using ontologies like Brick are vital for smart building applications, but querying them remains a challenge for practitioners. Knowledge Graph Question Answering (KGQA) systems, meant to retrieve answers from natural language questions, traditionally require large-scale training data, making them ill-suited for the specialized and data-scarce building domain. The advent of Large Language Models (LLMs) offers a paradigm shift, enabling zero-shot natural language querying without building/domain-specific training. Yet, there is no standardized benchmark for building-specific KGQA which can guide and validate research in this area. To address this gap, our work makes three primary contributions. First, we introduce the BuildingQA Benchmark Dataset, constructed through a multi-stage process of collecting practitioner data, augmenting it with LLMs for linguistic diversity, and curating a final set of 188 questions across 4 buildings. Second, we characterize the benchmark's complexity and ambiguity, introducing a novel method to quantify its "lexical gap" and providing a four-stage diagnostic framework for analyzing how systems fail. Third, we benchmark zero-shot LLM-powered KGQA systems to establish baseline performance and analyze their failure modes. Our evaluation reveals that top-performing systems achieve a maximum F1 score of only 0.38. This result does not indicate a failure of these powerful systems, but rather underscores the unique challenges posed by our benchmark. It demonstrates a critical performance gap, showing that current methods successful on general KGs struggle with the specific lexical and structural nuances of the building domain. BuildingQA1 thus provides the benchmark dataset and foundational analysis needed to drive the development of novel, domain-aware methods required to unlock the use of semantic data in buildings.

Mulayim, Ozan Baris↗
DOE OSTI2025

I Can’t Read All That! Improving the Usability of Semantic Models Using Concise, Ontology-Agnostic, Building-Specific Schemas

Semantic ontologies have enabled the creation of formalized, machine-readable descriptions of heterogenous building systems by providing dictionaries of well defined concepts that can be applied to model them. Within a semantic model of a particular building, a subset of an ontology's concepts may be applied in different ways to represent a particular perspective of the building's systems. How the concepts were applied can only be understood by examining the large amount of instance data within a semantic model, which leads to usability challenges. We propose a concise, ontology-agnostic method for defining building-specific schema (b-schema) graphs that summarize the structure and content of a semantic model. This approach provides a queryable and concise representation of the model's contents, separate from the instance data within a model, that can mitigate the challenges posed by the size and complexity of semantic models in processes such as visualization, querying, validation, and the use of large language models (LLMs). We validate our approach on semantic models based on the Brick and ASHRAE S223 ontologies. Results demonstrate that b-schemas significantly reduce the complexity of visual interpretation, accelerate SPARQL queries and SHACL validation, and improve LLM-based knowledge graph question answering.

Paul, Lazlo [Lawrence Berkeley National Laboratory↗
DOE OSTI2025

Poster Abstract: Leveraging Large Language Models to Reveal Interpretable Cooling Behaviors from Smart Thermostat Data

Frequent heatwaves and hot summers increasingly challenge occupant comfort, health, and energy grid stability. Addressing these challenges requires a detailed understanding of household cooling behaviors, such as thermostat adjustments and adaptive responses to extreme conditions. Traditional analyses often rely on aggregated numerical metrics that overlook subtle but important household-specific variations. In this study, we introduce a generalizable methodology that integrates large language models (LLMs) with vision capabilities to enable scalable and detailed analysis of residential thermostat data. Using Ecobee's Donate Your Data (DYD) dataset—which provides five-minute records of indoor temperatures, thermostat setpoints, and HVAC runtimes—we focus on two U.S. cities with contrasting summer climates : Austin (TX) and Phoenix (AZ). Because raw time-series data are not well suited for direct LLM analysis, we transform them into visual representations, such as daily indoor temperature trajectories and weekly runtime histograms, to better capture behavioral variations. Leveraging LLMs' visual interpretation, we extract descriptive behavioral features, including temperature preferences, time-of-day cooling orientation, anticipatory versus reactive heatwave responses, and behavioral consistency. These semantic features support unsupervised clustering to identify distinct occupant archetypes at scale, revealing differences—such as morning-centric anticipatory coolers versus households that shift toward warmer setpoints during heatwaves—that can inform demand response, resilience planning, and health-aware interventions. By converting raw numerical data into interpretable behavioral patterns, this methodology enables scalable and practical analysis of occupant behavior, supporting actionable insights for comfort, resilience, and energy management.

Nihar, Kopal↗
DOE OSTI2026

SetGo: Metadata Readiness for Scientific AI Datasets

Scientific datasets intended for AI use require both computational readiness for model training and metadata readiness for discovery, sharing, and reuse. The Readiness Engine for Data Integration (REDI) addresses computational readiness, but no corresponding tool evaluates whether a dataset’s metadata are sufficiently complete, governed, and standards-compliant for publication and agent-based consumption. Existing FAIR assessors operate only on published repository records, and no single system covers FAIR compliance, licensing, provenance, governance, reproducibility, and catalog readiness together. We present SetGo, an open-source Python toolkit that assesses and repairs metadata readiness across these six dimensions before a dataset is published or archived. Applied to four scientific corpora, SetGo surfaces deficiencies that general-purpose tools do not detect: ERA5 climate metadata scores 4% on ACDD 1.3 compliance; materials datasets fail OPTIMADE species-definition requirements; and PDB-derived proteomics data carries licensing terms incompatible with standard SPDX identifiers. Guided enrichment raises overall FAIR scores from 52–57% to 81–91%, and a single setgo publish command pushes to Hugging Face Hub, CKAN, or OpenMetadata with ML Commons Croissant 1.0 metadata sidecars. To support interactive and automated workflows, SetGo integrates with coding agents powered by large language models (LLMs) through a /setgo skill that enables natural-language execution of the full assess–enrich–publish loop, with user involvement limited to supplying missing metadata values.

Wilkinson, Sean [ORNL] (ORCID:0000000214437479)↗
DOE OSTI2025

Trajectory Balance with Asynchrony

Finetune large language models (LLMs) quicker via parallelization. Specifically, this implements asynchronous reinforcement learning with a trajectory balance objective function

Bartoldson, BrianR [Lawrence Livermore National La↗
DOE OSTI2025

tether

Tether is a python module for benchmarking and assessing large language model (LLMs) performance at generic scientific tasks. The code generates benchmarks, uses the benchmark to prompt LLMs through automatic programming interfaces (APIs), and then logs the number of prompts an LLM correctly answers and presents the results as a completed benchmark.

Kaiser, Bryan [Los Alamos National Laboratory]↗
DOE OSTI2025

Open AI Co-Scientist - Hypothesis Evolution System

An AI-powered system for generating, reviewing, ranking, and evolving research hypotheses. It leverages Large Language Models (LLMs) for various tasks, including hypothesis generation, reflection, and comparison. The system is designed to assist researchers in exploring a research space and identifying promising hypotheses.

Liao, Chunhua↗
DOE OSTI2025

3_wise_bears

This is a small set of python scripts and HTML that uses OpenAI API to control large language models (LLMs) working agentically to solve a posed question / problem. There are 3 agents and they work to get it "just right" by taking on various "roles" of friendly and adversarial critics. It repeats a number of times specified by the user, and then writes a report.

DeBardeleben, Nathan Andrew [Los Alamos National L↗