Search NASA⌕ Search

SEARCH · Search NASA

Results for “large language model fine tuning”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Assessment of fine-tuned large language models for real-world chemistry and material science applications

The current generation of large language models (LLMs) has limited chemical knowledge. Recently, it has been shown that these LLMs can learn and predict chemical properties through fine-tuning. Using natural language to train machine learning models opens doors to a wider chemical audience, as field-specific featurization techniques can be omitted. In this work, we explore the potential and limitations of this approach. We studied the performance of fine-tuning three open-source LLMs (GPT-J-6B, Llama-3.1-8B, and Mistral-7B) for a range of different chemical questions. We benchmark their performances against “traditional” machine learning models and find that, in most cases, the fine-tuning approach is superior for a simple classification problem. Depending on the size of the dataset and the type of questions, we also successfully address more sophisticated problems. The most important conclusions of this work are that, for all datasets considered, their conversion into an LLM fine-tuning training set is straightforward and that fine-tuning with even relatively small datasets leads to predictive models. These results suggest that the systematic use of LLMs to guide experiments and simulations will be a powerful technique in any research study, significantly reducing unnecessary experiments or computations.

Van Herck, Joren↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗
DOE OSTI2025

Explainable Synthesizability Prediction of Inorganic Crystal Polymorphs Using Large Language Models

Abstract We evaluate the ability of machine learning to predict whether a hypothetical crystal structure can be synthesized and explain those predictions to scientists. Fine‐tuned large language models (LLMs) trained on a human‐readable text description of the target crystal structure perform comparably to previous bespoke convolutional graph neural network methods, but better prediction quality can be achieved by training a positive‐unlabeled learning model on a text‐embedding representation of the structure. An LLM‐based workflow can then be used to generate human‐readable explanations for the types of factors governing synthesizability, extract the underlying physical rules, and assess the veracity of those rules. These explanations can guide chemists in modifying or optimizing non‐synthesizable hypothetical structures to make them more feasible for materials design.

Kim, Seongmin [Department of Chemical and Biologic↗
DOE OSTI2025

Explainable Synthesizability Prediction of Inorganic Crystal Polymorphs Using Large Language Models

Abstract We evaluate the ability of machine learning to predict whether a hypothetical crystal structure can be synthesized and explain those predictions to scientists. Fine‐tuned large language models (LLMs) trained on a human‐readable text description of the target crystal structure perform comparably to previous bespoke convolutional graph neural network methods, but better prediction quality can be achieved by training a positive‐unlabeled learning model on a text‐embedding representation of the structure. An LLM‐based workflow can then be used to generate human‐readable explanations for the types of factors governing synthesizability, extract the underlying physical rules, and assess the veracity of those rules. These explanations can guide chemists in modifying or optimizing non‐synthesizable hypothetical structures to make them more feasible for materials design.

Kim, Seongmin [Department of Chemical and Biologic↗
DOE OSTI2026

Agentic framework for programmatic crystal structure generation using a fine-tuned worker–supervisor large language model

Platinum group metals (PGMs) underpin many catalytic technologies but face severe supply constraints, motivating the search for alternative materials and computational methods to accelerate discovery. While atomistic simulation tools such as Pymatgen and ASE have streamlined structure manipulation, they require detailed inputs, limiting accessibility for experimentalists and slowing early-stage exploration. Here, in this study, we present an AI-driven agentic framework that orchestrates worker–supervisor large language models (LLMs). The worker translates natural-language prompts of varying abstraction into valid crystallographic structures using a compact LLM fine-tuned with low-rank adaptation on a curated text–code–CIF dataset, emphasizing energy-efficient training. Benchmarking against the baseline CodeGen-350M-mono model shows that fine-tuning reduces hallucination rates from 100% to as low as 5% and improves structural match accuracy to up to 82% for fully specified inputs. Accuracy declines with decreasing prompt detail but remains nontrivial even when only stoichiometry and space group are provided, underscoring the LLM’s capacity for crystallographic inference. The supervisor Claude LLM evaluates the outputs and triggers iterative refinement through the worker’s built-in structure manipulation capabilities (e.g., supercell scaling, strain, vacancy, and substitution operations). We further demonstrate use cases for technologically relevant catalysts, including IrO 2 , pyrochlore Pb 2 Ir 2 O 7 , Ni 2 FeO 4 , and Ni 3 Mo, where the framework generates physically consistent structures that can be refined via geometry optimization. This work introduces a low-energy, language-driven pathway for integrating human and machine intelligence in materials design, paving the way for AI-assisted synthesis planning and high-throughput screening of complex oxides.

AI agent↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗
NASA NTRS2024

Analyzing EOSDIS Dataset Research Outputs using Knowledge Graphs and Large Language Models

Datasets, unlike publications, can be updated over time, with each new version receiving a DOI but not always being linked to previous ones. This complicates tracking citations across a dataset’s lifecycle. We address this by integrating dataset versions and citations into a knowledge graph (KG), which helps trace dataset citations and analyze dataset usage in applied research. To categorize publications from various journals, we fine-tuned NASA IMPACT INDUS Large Language Model (LLM) on a labeled publication set, assigning publications to one of twenty applied research areas. By linking datasets to these research areas, we improved dataset searchability and discovery through these domains.

open-source↗
NASA NTRSDate not supplied

Discovering Research Areas in Dataset Applications Through Knowledge Graphs and Large Language Models

Scientific datasets are increasingly cited in peer-reviewed journal publications, facilitating easy access to research utilizing those datasets. Datasets undergo a life cycle where older versions of datasets are replaced by newer versions often due to improvements in data resolution, algorithms, and other factors. Unlike peer reviewed documents registered with a single Digital Unique Identifier (DOI), datasets can be updated over time and the newer version of the datasets are registered with a new DOI which is not necessarily linked to the previous version of the dataset. It is challenging when publications citing a dataset need to be traced over the entire life cycle of that dataset. We provide an innovative approach to link the dataset versions and publications using a knowledge graph (KG). KG can help to trace the dataset cited in publications over the entire dataset life cycle and shed light into dataset usage in various applied research areas. We fine-tuned the pretrained NASA IMPACTINDUS Large Language Model (LLM) on a set of labeled publications abstracts. Our results showed that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were classified into non-applied research areas. By linking datasets to applied research areas through the KG and employing Global Change Master Directory(GCMD), a well-established controlled vocabulary of scientific keywords describing Earth science datasets, we contribute to a transparent and advanced search and discovery mechanism for datasets across the Earth data ecosystem. The integrated KG and LLM approach is now incorporated and operational in dataset publication management at one of NASA’s Earth science data archival centers.

data provenance↗
DOE OSTI2025

Achieving GPT-4o level performance in astronomy with a specialized 8B-parameter large language model

AstroSage-Llama-3.1-8B is a domain-specialized natural-language AI assistant tailored for research in astronomy, astrophysics, cosmology, and astronomical instrumentation. Trained on the complete collection of astronomy-related arXiv papers from 2007 to 2024 along with millions of synthetically-generated question-answer pairs and other astronomical literature, AstroSage-Llama-3.1-8B demonstrates remarkable proficiency on a wide range of questions. AstroSage-Llama-3.1-8B scores 80.9% on the AstroMLab-1 benchmark, greatly outperforming all models—proprietary and open-weight—in the 8-billion parameter class, and performing on par with GPT-4o. This achievement demonstrates the potential of domain specialization in AI, suggesting that focused training can yield capabilities exceeding those of much larger, general-purpose models. AstroSage-Llama-3.1-8B is freely available, enabling widespread access to advanced AI capabilities for astronomical education and research.

AI assistant↗
DOE OSTI2026

Genomic Language model for Annotation of Repetitive Elements (GLARE) v1.0

GLARE (Genomic Language model for Annotation of Repetitive Elements) is a tool that classifies transposable elements (TEs)—the mobile, repetitive DNA sequences that make up large fractions of eukaryotic genomes. GLARE fine-tunes the NTv3-650M genomic language model on a harmonized collection of curated TE sequences from the PanTEon and Repbase reference databases, assigning each input sequence to one of 11 orders and 32 superfamilies in a Wicker-compatible taxonomy. Features. From nucleotide FASTA input, GLARE outputs per-sequence predictions, class summaries, composition figures, and an annotated FASTA. It provides calibrated confidence scores with optional abstention and runs on CPU or GPU. Uses. GLARE serves as a classification component in genome-annotation pipelines, downstream of TE discovery, supporting genome annotation and comparative and evolutionary genomics. Advantages. GLARE is the first repeat-element classifier to leverage a pretrained genomic language model. Combined with multi-database training, this approach outperformed all nine classifiers in the PanTEon benchmark, generalized better to unseen taxonomic clades, and remained robust to sequence orientation—a common failure mode of existing tools.

Bruna, Tomas [Lawrence Berkeley National Laborator↗
DOE OSTI2024

Structured information extraction from scientific text with large language models

Extracting structured knowledge from scientific text remains a challenging task for machine learning models. Here, we present a simple approach to joint named entity recognition and relation extraction and demonstrate how pretrained large language models (GPT-3, Llama-2) can be fine-tuned to extract useful records of complex scientific knowledge. We test three representative tasks in materials chemistry: linking dopants and host materials, cataloging metal-organic frameworks, and general composition/phase/morphology/application information extraction. Records are extracted from single sentences or entire paragraphs, and the output can be returned as simple English sentences or a more structured format such as a list of JSON objects. This approach represents a simple, accessible, and highly flexible route to obtaining large databases of structured specialized scientific knowledge extracted from research papers.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
NASA NTRSDate not supplied

Enhancing Dataset Discovery and Usage Tracking in Earth Sciences: Integrating Knowledge Graphs and Large Language Models

NASA's Data Active Archive Centers (DAACs) have played a crucial role in supporting a wide range of applied research in Earth and Environmental sciences. To date, over 20,000 publications have been collected, citing more than 3,000 NASA Earth science datasets. We present an innovative approach that links datasets and collected publications through a knowledge graph (KG). This KG enables the tracking of dataset citations throughout the dataset's lifecycle, revealing patterns of dataset usage across various applied research areas. We fine-tuned the pre-trained NASA IMPACT INDUS-Base Retriever Large Language Model (LLM) using a set of labeled publication abstracts. Our results indicate that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were categorized into non-applied research areas. The classified publications linked to datasets are used to discover datasets by users interested in specific applied research and by dataset providers to determine dataset usage for applications.

open-source↗
DOE OSTI2026

SmileyLlama: modifying large language models for directed chemical space exploration

Here we show that large language models (LLMs) can be transformed via supervised fine-tuning of engineered prompts into SmileyLlama for exploring the chemical space of drug molecules. We benchmark SmileyLlama against pretrained LLMs and chemical language models trained from scratch for generating valid and novel drug-like molecules, and use direct preference optimization to both improve SmileyLlama’s adherence to a prompt and as part of the iMiner reinforcement learning framework to predict molecules with optimized three-dimensional conformations and high binding affinity to drug targets. By training an LLM to speak directly as a chemical language model, while retaining most of its natural language capabilities, we show that SmileyLlama can reliably generate molecules with user-specified properties rather than acting only as a chatbot with knowledge of chemistry or as a virtual assistant. While SmileyLlama is geared toward drug discovery, the supervised fine-tuning/direct preference optimization/LLM framework can be extended to other chemical, biological and materials applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

The role of chromatin state in intron retention: A case study in leveraging large scale deep learning models

Complex deep learning models trained on very large datasets have become key enabling tools for current research in natural language processing and computer vision. By providing pre-trained models that can be fine-tuned for specific applications, they enable researchers to create accurate models with minimal effort and computational resources. Large scale genomics deep learning models come in two flavors: the first are large language models of DNA sequences trained in a self-supervised fashion, similar to the corresponding natural language models; the second are supervised learning models that leverage large scale genomics datasets from ENCODE and other sources. We argue that these models are the equivalent of foundation models in natural language processing in their utility, as they encode within them chromatin state in its different aspects, providing useful representations that allow quick deployment of accurate models of gene regulation. We demonstrate this premise by leveraging the recently created Sei model to develop simple, interpretable models of intron retention, and demonstrate their advantage over models based on the DNA language model DNABERT-2. Our work also demonstrates the impact of chromatin state on the regulation of intron retention. Using representations learned by Sei, our model is able to discover the involvement of transcription factors and chromatin marks in regulating intron retention, providing better accuracy than a recently published custom model developed for this purpose.

Biochemistry & Molecular Biology↗
DOE OSTI2021

NukeLM: Pre-Trained and Fine-Tuned Language Models for the Nuclear and Energy Domains

Natural language processing (NLP) tasks (text classification, named entity recognition, etc.) have seen amazing improvements over the last few years. This is due to models such as BERT that achieve deep knowledge transfer by using a large pre-trained model, then fine-tuning the model on specific tasks. The BERT architecture has shown even better performance on domain-specific tasks when the model is pre-trained using domain-relevant texts. Here, inspired by these recent advancements, we have developed NukeLM, a nuclear-domain BERT model pre-trained on 1.5 million abstracts from the DOE Office of Scientific and Technical Information (OSTI) database. This NukeLM model is then fine-tuned for the classification of research articles into either binary classes (related to the nuclear fuel cycle (NFC) or not) or multiple categories related to the subject of the article. We show that continued pre-training of a BERT-style architecture prior to fine-tuning results in greater performance in both article classification tasks. This information is critical for properly triaging manuscripts, a necessary task for better understanding citation networks that publish in the nuclear space and uncovering new areas of research in the nuclear (or nuclear relevant) domain.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2025

LLaMP v0.1.0

Reducing hallucination of Large Language Models (LLMs) is imperative for use in the sciences, where reliability and reproducibility are crucial. However, LLMs inherently lack long-term memory, making it a nontrivial, ad hoc, and inevitably biased task to fine-tune them on domain-specific literature and data. LLaMP is a multimodal retrieval-augmented generation (RAG) framework of hierarchical reasoning and acting (ReAct) agents that can dynamically and recursively interact with Materials Project to ground large language models on high-fidelity materials informatics.

Riebesell, Janosh [Lawrence Berkeley National Labo↗