SEARCH · Engineering Papers

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.

SourceResearch connectionFrom yearThrough year

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

At least 433 records · Page 24

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Large Language Model Integration for Knowledge Retrieval and Interaction for the DUNE Experiment

The Deep Underground Neutrino Experiment (DUNE) is a next-generation neutrino experiment that will generate an unprecedented volume of heterogeneous information-from documentation and technical notes to experimental data and reconstruction pipelines. Efficient knowledge retrieval and contextual understanding are increasingly critical for collaboration-wide productivity and onboarding. In this work, we present DUNE-GPT, a prototype framework that leverages large language models (LLMs) and retrieval-augmented generation (RAG) to enable natural-language querying of DUNE's internal documentation and technical resources. The system provides an intelligent interface for DUNE collaborators to interact with experiment-specific knowledge while maintaining data privacy and infrastructure compliance within Fermilab computing resources.

Rafique, A. [Argonne (main)]↗

DOE OSTI2026

Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models

Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs. To better understand LLM scaling, we study representational differences between LLMs and their smaller counterparts, with the goal of replicating the representational qualities of larger models in smaller models. We observe a geometric phenomenon which we term embedding condensation, where token embeddings collapse into a narrow cone-like subspace in some language models. Through systematic analyses across multiple Transformer families, we show that small models such as GPT2 and Qwen3-0.6B exhibit severe condensation, whereas larger models such as GPT2-x1 and Qwen3-32B are more resistant to this phenomenon. Additional observations show that embedding condensation is not reliably mitigated by knowledge distillation from larger models. To fight against it, we formulate a dispersion loss that explicitly encourages embedding dispersion during training. Experiments demonstrate that it mitigates condensation, recovers dispersion patterns seen in larger models, and yields performance gains across 10 benchmarks. We believe this work offers a principled path toward improving smaller Transformers without additional parameters.

Xiao, Xi [ORNL] (ORCID:0009000009316982)↗

NASA NTRSDate not supplied

Trust-Informed Large Language Models via Word Embedding-Knowledge Graph Alignment

A major weakness of a Large Language Model (LLM) is its tendency to accept information at face value, often leading to injection of erroneous information and inducing a greater probability of hallucinating non-existent information. While Retrieval Augmented Generation (RAG) uses external knowledge sources to bolster LLMs through grounded truth, this work seeks to explore methods to engender a LLM with an intrinsic capability to evaluate an input’s believability without relying on external knowledge sources. We investigate unifying a LLM with a Knowledge Graph (KG) and using the KG to reinforce the LLM’s internal word embedding while also maintaining belief metrics along the edge’s in the KG.

Large Language Model↗

DOE OSTI2025

Leveraging large language models to automate the identification of healthcare access barriers for veterans

Objective: To develop and evaluate an automated system for identifying healthcare barriers focusing on transportation issues in veterans’ clinical notes using large language models (LLMs) and to assess the impact of different prompting strategies on classification performance and explanation consistency. Methods: We developed a hybrid system combining pattern matching for templated notes with LLM analysis for free-text notes. Using 2000 manually annotated clinical notes, we compared four prompting strategies (dual-role short, dual-role long, analysis-first, analysis-only) across Mistral-7B and Llama-3.1 models. We evaluated classification performance using standard metrics and assessed explanation consistency through embedding similarity analysis. Results: The analysis-first strategy achieved superior performance, with Mistral-7B reaching an F1 score of 0.914, outperforming traditional machine learning approaches (GBM: 0.786, BERT: 0.811). LLMs demonstrated higher explanation consistency within models (mean cosine similarity 0.887–0.908) compared to cross-model similarities (0.767–0.872). Pattern matching successfully handled 6.7% of templated notes deterministically. Mistral-7B showed greater internal consistency but higher abstention rates compared to Llama-3.1. Conclusion: Requiring LLMs to analyze evidence before classification improves both accuracy and explanation consistency for identifying transportation barriers in clinical notes. This approach enables automated barrier detection at scale while providing clinically relevant explanations, supporting both population-level healthcare planning and individual patient care decisions.

Healthcare access barriers↗

DOE OSTI2024

Sentiment analysis of the United States public support of nuclear power on social media using large language models

This study utilized large language models (LLMs) to analyze public sentiment in the United States (US) regarding nuclear power on social media, focusing on X/Twitter, considering climate change challenges and advancements in nuclear power technology. Approximately, 1.26 million nuclear tweets from 2008–2023 were examined to fine-tune LLMs for sentiment classification. We found the crucial role of accurate data labeling for model performance, with potential implications for a 15% improvement, achieved through high-confidence labels. LLMs demonstrated better performance compared to traditional machine learning classifiers, with reduced susceptibility to overfitting and up to 96% classification accuracy. LLMs are used to segment the US public tweets into policy and energy-related categories, revealing that 68% are politically themed. Policy tweets tended to convey negative sentiment, often reflecting opposing political perspectives and focusing on nuclear deals and international relations. Energy-related tweets covered diverse topics with predominantly neutral to positive sentiment, indicating broad support for nuclear power in 48 out of 50 US states. The US public positive sentiments toward nuclear power stemmed from its high power density, reliability regardless of weather conditions, environmental benefits, application versatility, and recent innovations and advancements in both fission and fusion technologies. Negative sentiments primarily focused on waste management, high capital costs, and safety concerns. The neutral campaign highlighted global nuclear facts and advancements, with varying tones leaning towards positivity or negativity. An interesting neutral theme was the advocacy for the combined use of renewable and nuclear energy to attain net-zero goals.

Energy & Fuels↗

DOE OSTI2020

Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)–based ranking for concept normalization

Concept normalization, the task of linking phrases in text to concepts in an ontology, is useful for many downstream tasks including relation extraction, information retrieval, etc. We present a generate-and-rank concept normalization system based on our participation in the 2019 National NLP Clinical Challenges Shared Task Track 3 Concept Normalization. The shared task provided 13 609 concept mentions drawn from 100 discharge summaries. We first design a sieve-based system that uses Lucene indices over the training data, Unified Medical Language System (UMLS) preferred terms, and UMLS synonyms to generate a list of possible concepts for each mention. We then design a listwise classifier based on the BERT (Bidirectional Encoder Representations from Transformers) neural network to rank the candidate concepts, integrating UMLS semantic types through a regularizer. Our generate-and-rank system was third of 33 in the competition, outperforming the candidate generator alone (81.66% vs 79.44%) and the previous state of the art (76.35%). During postevaluation, the model’s accuracy was increased to 83.56% via improvements to how training data are generated from UMLS and incorporation of our UMLS semantic type regularizer. Analysis of the model shows that prioritizing UMLS preferred terms yields better performance, that the UMLS semantic type regularizer results in qualitatively better concept predictions, and that the model performs well even on concepts not seen during training. Our generate-and-rank framework for UMLS concept normalization integrates key UMLS features like preferred terms and semantic types with a neural network–based ranking model to accurately link phrases in text to UMLS concepts.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2023

Deep learning-enabled natural language processing to identify directional pharmacokinetic drug–drug interactions

Background. During drug development, it is essential to gather information about the change of clinical exposure of a drug (object) due to the pharmacokinetic (PK) drug-drug interactions (DDIs) with another drug (precipitant). While many natural language processing (NLP) methods for DDI have been published, most were designed to evaluate if (and what kind of) DDI relationships exist in the text, without identifying the direction of DDI (object vs. precipitant drug). Here we present a method for the automatic identification of the directionality of a PK DDI from literature or drug labels. Methods. We reannotated the Text Analysis Conference (TAC) DDI track 2019 corpus for identifying the direction of a PK DDI and evaluated the performance of a fine-tuned BioBERT model on this task by following the training and validation steps prespecified by TAC. Results. This initial attempt showed the model achieved an F-score of 0.82 in identifying sentences as containing PK DDI and an F-score of 0.97 in identifying object versus precipitant drugs in those sentences. Discussion and conclusion. Despite a growing list of NLP methods for DDI extraction, most of them use a common set of corpora to perform general purpose tasks (e.g., classifying a sentence into one of several fixed DDI categories). There is a lack of coordination between the drug development and biomedical informatics method development community to develop corpora and methods to perform specific tasks (e.g., extract clinical exposure changes due to PK DDI). We hope that our effort can encourage such a coordination so that more “fit for purpose” NLP methods could be developed and used to facilitate the drug development process.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Improving Text Classification with Large Language Model-Based Data Augmentation

Large Language Models (LLMs) such as ChatGPT possess advanced capabilities in understanding and generating text. These capabilities enable ChatGPT to create text based on specific instructions, which can serve as augmented data for text classification tasks. Previous studies have approached data augmentation (DA) by either rewriting the existing dataset with ChatGPT or generating entirely new data from scratch. However, it is unclear which method is better without comparing their effectiveness. This study investigates the application of both methods to two datasets: a general-topic dataset (Reuters news data) and a domain-specific dataset (Mitigation dataset). Our findings indicate that: 1. ChatGPT generated new data consistently enhanced model’s classification results for both datasets. 2. Generating new data generally outperforms rewriting existing data, though crafting the prompts carefully is crucial to extract the most valuable information from ChatGPT, particularly for domain-specific data. 3. The augmentation data size affects the effectiveness of DA; however, we observed a plateau after incorporating 10 samples. 4. Combining the rewritten sample with new generated sample can potentially further improve the model’s performance.

97 MATHEMATICS AND COMPUTING↗

NASA NTRSDate not supplied

Contextualizing Air Traffic Management Conversations using Natural Language Understanding

Efficient management of air traffic and mitigation of delays depend on extracting actionable information from unstructured data, such as dialogues from the Federal Aviation Administration’s (FAA’s) Air Traffic Control System Command Center (ATCSCC) telecons. This study presents a pipeline utilizing Natural Language Processing (NLP) methods for Intent Classification (IC) and Slot Filling (SF) to identify and extract Traffic Management Initiatives (TMIs) from aviation-specific dialogues. We leveraged DeBERTa, a pre-trained transformer model, and fine-tuned it to the nuances of the aviation domain. Despite challenges posed by annotation complexities, the IC model achieved promising results with a weighted average F1-score of 0.81. Our results are close to those of human annotators, which demonstrates the model’s strong alignment with human-level performance. The SF model also showed strong performance, achieving a weighted F1-score of 0.97, which demonstrates its effectiveness in accurately predicting key slots. Our analysis revealed limitations in handling less frequent intents and slot labels due to data sparsity, motivating future efforts to adopt joint IC-SF modeling and data augmentation strategies. This research highlights the potential of domain-specific NLP to streamline decision-making in the aviation industry and improve the management of TMIs.

Air Traffic Control Management↗

DOE OSTI2025

Leveraging Large Language Models for Real-World Data Evidence: A Framework for Automated Treatment Extraction and Data Harmonization

Background: The ability to comprehensively collect treatment information from cancer patient medical records would enable studies to evaluate real-world benefits and risks tied to specific treatments. Currently, it is difficult to system- atically collect high-quality treatment information because it is often stored in unstructured text. Manually extracting and standardizing drug and regimen data is time-intensive. Recent advances in large language models (LLMs) offer a potential solution for automated extraction of structured treatment information from clinical text. Objective: This study systematically evaluates the utility of four LLMs from the Llama family for automated extraction of oncology treatment information from clinical text. This information can guide researchers using cancer registry data to provide insights into cancer care and outcomes beyond clinical trials. Methods: Four instruction-tuned Llama models with varying parameter counts (1B, 3B, 8B, and 70B) were evaluated for their ability to extract treatment information from clinical documents. A unified oncology knowledge base integrating seven major public data sources was developed to standardize and normalize extracted entities—a critical step for harmonizing data from diverse sources. Extracted treatment data were compared against expert-annotated ground truth. Model performance was assessed using accuracy metrics (Precision, Recall, F1-Score) and opera- tional feasibility metrics, including processing speed and structural compliance of the output. Results: A strong positive correlation was observed between model size and extraction accuracy. F1-score improved from 0.609 for the 1B model to 0.710 (3B), 0.807 (8B), and 0.828 (70B). While larger models demonstrated superior accuracy and compliance, they incurred higher computational costs. The modest performance difference between 8B and 70B suggests diminishing returns with increasing model size. Conclusions: LLMs represent a viable technology for automating oncology treatment extraction. The 8B-parameter model emerged as a highly effective option, balancing high accuracy and computational efficiency. Selecting an appropriate LLM for deployment in cancer registries involves a trade-off between desired accuracy and available operational resources. Harmonizing extracted entities with the oncology knowledge base facilitates standardized integration into common data models, enhancing data quality for real-world evidence analyses.

artificial intelligence↗

DOE OSTI2018

Integrating Natural Language Processing and Machine Learning Algorithms to Categorize Oncologic Response in Radiology Reports

A significant volume of medical data remains unstructured. Natural language processing (NLP) and machine learning (ML) techniques have shown to successfully extract insights from radiology reports. However, the codependent effects of NLP and ML in this context have not been well-studied. Between April 1, 2015 and November 1, 2016, 9418 cross-sectional abdomen/pelvis CT and MR examinations containing our internal structured reporting element for cancer were separated into four categories: Progression, Stable Disease, Improvement, or No Cancer. We combined each of three NLP techniques with five ML algorithms to predict the assigned label using the unstructured report text and compared the performance of each combination. The three NLP algorithms included term frequency-inverse document frequency (TF-IDF), term frequency weighting (TF), and 16-bit feature hashing. The ML algorithms included logistic regression (LR), random decision forest (RDF), one-vs-all support vector machine (SVM), one-vs-all Bayes point machine (BPM), and fully connected neural network (NN). The best-performing NLP model consisted of tokenized unigrams and bigrams with TF-IDF. Increasing N-gram length yielded little to no added benefit for most ML algorithms. With all parameters optimized, SVM had the best performance on the test dataset, with 90.6 average accuracy and F score of 0.813. The interplay between ML and NLP algorithms and their effect on interpretation accuracy is complex. The best accuracy is achieved when both algorithms are optimized concurrently.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2018

Automated Radiology Report Summarization Using an Open-Source Natural Language Processing Pipeline

Diagnostic radiologists are expected to review and assimilate findings from prior studies when constructing their overall assessment of the current study. Radiology information systems facilitate this process by presenting the radiologist with a subset of prior studies that are more likely to be relevant to the current study, usually by comparing anatomic coverage of both the current and prior studies. It is incumbent on the radiologist to review the full text report and/or images from those prior studies, a process that is time-consuming and confers substantial risk of overlooking a relevant prior study or finding. This risk is compounded when patients have dozens or even hundreds of prior imaging studies. Our goal is to assess the feasibility of natural language processing techniques to automatically extract asserted and negated disease entities from free-text radiology reports as a step towards automated report summarization. We compared automatically extracted disease mentions to a gold-standard set of manual annotations for 50 radiology reports from CT abdomen and pelvis examinations. The automated report summarization pipeline found perfect or overlapping partial matches for 86% of the manually annotated disease mentions (sensitivity 0.86, precision 0.66, accuracy 0.59, F1 score 0.74). The performance of the automated pipeline was good, and the overall accuracy was similar to the interobserver agreement between the two manual annotators.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

DOE OSTI2026

Cross-domain digital twin architecture for predictive maintenance via machine learning and Large Language Models

This research introduces a comprehensive framework for creating and deploying a digital twin platform for continuous monitoring and predictive maintenance within industrial settings. Through utilizing advanced technologies, including Unreal Engine 5, Unity 3D, the Message Queue Telemetry Transport protocol, Random Forest machine learning algorithms, and Large Language Models (LLMs), we establish a platform that digitally reproduces physical equipment and translates digital controls into real-world actions. This facilitates preventive maintenance approaches and improves operational effectiveness. The digital twin platform gathers sensor data from operational equipment, analyzes it using machine learning, and delivers practical insights to prevent potential malfunctions and enhance equipment performance. Furthermore, the incorporation of a web portal enables efficient monitoring and access to historical data, educational materials, and equipment status information. Preliminary findings indicate that digital twins can transform industrial equipment management and maintenance methodologies.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Generative large language models for predictive maintenance planning

Maintenance planning and the generation of necessary components for tasks can prove time-consuming and complex. Automating the creation of recurring or similar tasks by leveraging previous planning packages and data, while uncovering insights to automate planning package generation, presents an opportunity to conserve valuable time and resources. This work aims to harness the textual and probabilistic capabilities of large language models (LLMs) to automate the generation of planning packages. Utilizing diverse data sources ranging from raw data to handwritten text, both singular and collaborative LLMs are trained and tested. Results demonstrate their capability to generate essential planning package components, effectively replicating the statistical patterns in the data. This demonstrates the use of these tools inside a digital asset for automated planning. This work outlines a methodology for constructing datasets, a training suite, and evaluation methods for LLM-based textual and conversational planning tools utilized in an asset digital twin. Results indicate that the fine-tuned models generate estimated planning information within the statistical ranges observed in real maintenance data. The models achieve high accuracy (>90%) in document question-answering and instruction generation tasks. Furthermore, the conversational retrieval-augmented generation (RAG) assistant system achieves 100% document retrieval accuracy, while conversational information capture exceeds 98% across the majority of work-package assistant modules.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Large language model-driven database for thermoelectric materials

Thermoelectric materials have the ability to convert waste heat into electricity, offering a valuable solution for energy harvesting. However, their widespread use is hindered by low conversion efficiency, the reliance on expensive rare earth elements, and the environmental and regulatory concerns associated with lead-based materials. A fast and cost-effective way to identify highly efficient thermoelectric materials is through data-driven methods. These approaches rely on robust and comprehensive datasets to train models. Although there are several databases on thermoelectric materials, there is still a need to collect and integrate experimental data from peer-reviewed research articles to capture diverse compositions and properties of materials. Here, in this work, we developed a comprehensive database of 7,123 thermoelectric compounds, containing key information such as chemical composition, structural detail, seebeck coefficient, electrical and thermal conductivity, power factor, and figure of merit (ZT). We used the GPTArticleExtractor workflow, powered by large language models (LLM), to extract and curate data automatically from the scientific literature published in Elsevier journals. This process enabled the creation of a structured database that addresses the challenges of manual data collection. The open access database could stimulate data-driven research and advance thermoelectric material analysis and discovery.

Database↗

DOE OSTI2026

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗

DOE OSTI2025

Automatic building energy model development and debugging using large language models agentic workflow

Building energy modeling (BEM) is a complex process that demands significant time and expertise, limiting its broader application in building design and operations. While Large Language Models (LLMs) agentic workflow have facilitated complex engineering processes, their application in BEM has not been specifically explored. This paper investigates the feasibility of automating BEM using LLM agentic workflow. Here, we developed a generic LLM-planning-based workflow that takes a building description as input and generates an error-free EnergyPlus building energy model. Our robust workflow includes four core agents: 1) Building Description Pre-Processing, 2) IDF Object Information Extraction, 3) Single IDF Object Generator Suite, and 4) IDF Debugging Agent. These agents divide the complex tasks into manageable sub-steps, enabling LLMs to generate accurate and reliable results at each stage. The case study demonstrates the successful translation of a building description into an error-free EnergyPlus model for the iUnit modular building at the National Renewable Energy Laboratory. The effectiveness of our workflow surpasses: 1) naive prompt engineering, 2) other LLM-based workflows, and 3) manual modeling, in terms of accuracy, reliability, and time efficiency. The paper concludes with a discussion on the interplay between foundational models and LLM agent planning design, advocating for the use of fine-tuned, specialized models to advance this field.

97 MATHEMATICS AND COMPUTING↗

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↗