Developing an Evaluation Framework for Assessing Large-Language Models in the Climate Domain
Explore the source record for details and available documents.
Patel, Kajal Paril↗
SEARCH · Search NASA
Results for “Large-language model”
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.
Demystifying the Resilience of Large Language Models: An End-to-End Perspective
Deep neural networks are known to be resilient to random bit-wise faults in their parameters. However, this resilience has primarily been established through evaluations of classification models. The extent to which this claim holds for large-language models remains underexplored. In this work, we conduct an extensive measurement study on the impact of random bitwise faults in commercial-scale language models. We perform an in-depth analysis of the resulting generation outputs. We first expose that these language models are not truly resilient to random bit-flips. While aggregate metrics such as accuracy may suggest resilience, an in-depth inspection of the generated outputs shows significant degradation in text quality. Our analysis also shows that tasks requiring more complex reasoning suffer more from performance and quality degradation. Moreover, we extend our analysis to models with augmented reasoning capabilities, such as Chain-of-Thought or Mixture of Experts architectures, and characterize their failure scenarios under random bit-flips.
Sun, Yu↗
A Preliminary Study on the Feasibility of Large Language Models for Detecting Micro-Behaviors Among Team Members in Space Missions
Large-language models (LLMs) have been recently used for spoken language understanding (SLU) to infer meaning and semantics from speech in tasks such as speaker intent and sentiment classification. Due to being trained on large amounts of data, and their ability to understand context and relationships between words, LLMs are competent, enabling them to generalize across tasks without requiring many task-specific training samples. This research examines the feasibility of few-shot learning in LLMs for detecting subtle, brief, and possibly unconscious interactions between team members, called ``micro-behaviors," and provides insights into the appropriate design of LLMs for this task. Our data came from 5 teams participating in a 45-day mission at the US National Aeronautics and Space Administration’s (NASA) Human Exploration Research Analog (HERA). More specifically we used data collected from team interaction battery (TIB) tasks teams performed five times in-mission which comprise an average 1.5 hours of conversation data per day. Micro-behaviors were coded according to an adapted version of Smith & Griffins (2022) theoretical framework in terms of Violation (i.e., presence of valenced behavior, uplifting/positive or discouraging/negative), Intensity (i.e., force of behavior in terms of how uplifting or discouraging is the behavior), and Intent (i.e., motive of the behavior in terms of whether it was deliberate or unintentional). We explore the ability of LLMs to detect the presence and intensity of micro-behaviors. We examine employing and fine-tuning readily available LLMs (i.e., RoBERTa, DistilBERT), as well as prompting state-of-the-art sequence classification models (i.e., Llama-2, Llama-3). In a total of 13,058 conversational turns (17.8% uplifting, 3.3% discouraging, 75.76% neutral, 3.14% nulls), we compute the macro F1-score of the 3-way micro-behavior classification task (i.e., classifying among uplifting, discouraging, and neutral; 33% chance). Results indicate that the RoBERTa model achieves a F1-score of 36.2% (uplift: 43.3% precision (P), 15.1% recall (R); discourage: 20% P, 0.5% R). These results significantly improve when we augment the data via paraphrasing in the RoBERTa model, reaching a 41.2% macro F1-score (uplift: 37.7% P, 86.3% R; discourage: 3.5% P, 1.8% R). Finally, the Llama-2 model with 3-shot prompting yields 38% macro F1-score (uplift: 28.7% P, 20% R; discourage: 7.2% P, 18% R), which is slightly better compared to the RoBERTa model without data augmentation, highlighting the effectiveness of sequence classification models in detecting minority classes with a small sample size. Findings indicate that LLMs hold potential to detect subtle behaviors in conversations, which could be valuable in assessing team behavior in space exploration missions. Future studies will evaluate the performance of different LLM prompting strategies or fine-tuning methods.
Ankush Raut↗
CALMS: CONTEXT-AWARE LANGUAGE MODEL FOR SCIENCE
Context-Aware Language Model for Science (CALMS) is designed to assist scientists with instrument operations and complex experimentation. CALMS consists of a large-language model (LLM) augmented with context and tool use abilities. With the ability to retrieve relevant information from facility documentation, CALMS can answer simple questions on scientific capabilities and other operational procedures. With the ability to interface with software tools and experimental hardware, CALMS can operate scientific instruments in a conversational manner.
CHERUKARA, MATTHEW↗
FAIR to WISE (F2W) v1.0.0
FAIR to WISE (F2W) is an iterative, large-language model (LLM) driven pipeline that turns unstructured research PDFs into structured, queryable knowledge graphs (KGs). Core features include schema-driven extraction to a LinkML model; full provenance capture; ontology-grounded enrichment (e.g., chemical validation and ChEBI lookup); graph construction to JSON-LD with stable IDs; and KG-RAG question answering with evidence-aware retrieval. The system is engineered for reproducibility and accessibility (open-source Ollama models, temperature=0, NVTX/Nsight profiling) with robust QA (relation verification, deduplication, and deterministic outputs). Primary uses are literature-to-KG automation, knowledge-grounded Q&A, and experimental steering support. We demonstrate the approach in organic photovoltaics, where the pipeline ingests papers, builds a domain KG, and evaluates answers against expert competency questions to guide experimental planning and interpretation. Compared with off-the-shelf LLMs and ad-hoc NLP tools, F2W addresses ontology gaps and reduces hallucination risk by grounding responses in extracted evidence and enforcing schema constraints; it also offers deterministic, provenance-linked outputs and open, cost-aware deployment. Evidence-aware ranking further improves answer quality over pure vector search.
Abramov, David [Lawrence Berkeley National Laborat↗
Memcomputing the Spectrum of Correlated Quantum Systems
The goals and objectives of the grant DE‐SC0020892 were to apply a new computing paradigm, MemComputing, to efficiently simulate properties of correlated quantum systems. The method has been applied to a wide set of problems ranging from quantum state tomography to finding the ground state of correlated systems. In all cases, substantial advantages compared to state-of-the-art approaches have been obtained. The project has also led to the suggestion of the transformer architecture (used nowadays in large-language models) as an efficient quantum state representation, and a better understanding of the role of memory in the generation of long-range order in neural networks. This grant has supported the work of a PhD student, inspired a new class on unconventional computing taught at the University of California, San Diego and has generated several peer-reviewed papers.
97 MATHEMATICS AND COMPUTING↗
Generative AI for Grid Operations [Slides]
In the last few years, the development and use of generative artificial intelligence (AI) and large-language models (LLMs) have changed the landscape of how AI and machine learning (ML) are being used in power systems. LLMs are built on foundational models based on large data sets that can be trained to provide information rapidly and through simple natural language prompts. Generative AI can then perform human-like tasks using ML models to identify and mimic pattens in the data sets. This presentation explores how generative AI can enhance grid operations by improving forecasts, enabling rapid contingency analyses, and offering real-time operational suggestions. By providing grid operators with valuable insights, generative AI will empower them to manage power systems more effectively.
24 POWER TRANSMISSION AND DISTRIBUTION↗
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↗