Search NASA⌕ Search

SEARCH · Search NASA

Results for “LLMs for design”

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.

7 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2025

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↗
NASA NTRSDate not supplied

Retrieval-Augmented Generation and LLM Agents for Biomimicry Design Solutions

We present BIDARA, a Bio-Inspired Design And Research Assistant, to address the complexity of biomimicry – the practice of designing modern-day engineering solutions inspired by biological phenomena. Large Language Models (LLMs) have been shown to act as sufficient general purpose task solvers, but they often hallucinate and fail in regimes that require domain-specific and up-to-date knowledge. We integrate Retrieval-Augmented Generation (RAG) and Reasoning-and-Action agents to aid LLMs in avoiding hallucination and utilizing updated knowledge during generation of biomimetic design solutions. We find that incorporating RAG increases the feasibility of the design solutions in both prompting and agent settings, and we use these findings to guide our ongoing work. To the extent of our knowledge, this is the first work that integrates and evaluates Retrieval-Augmented Generation within LLM-generated biomimetic design solutions.

biomimicry↗
NASA NTRSDate not supplied

Retrieval-Augmented Generation and LLM Agents for Biomimicry Design Solutions

We present BIDARA, a Bio-Inspired Design And Research Assistant, to address the complexity of biomimicry – the practice of designing modern-day engineering solutions inspired by biological phenomena. Large Language Models (LLMs) have been shown to act as sufficient general purpose task solvers, but they often hallucinate and fail in regimes that require domain-specific and up-to-date knowledge. We integrate Retrieval-Augmented Generation (RAG) and Reasoning-and-Action agents to aid LLMs in avoiding hallucination and utilizing updated knowledge during generation of biomimetic design solutions. We find that incorporating RAG increases the feasibility of the design solutions in both prompting and agent settings, and we use these findings to guide our ongoing work. To the extent of our knowledge, this is the first work that integrates and evaluates Retrieval-Augmented Generation within LLM-generated biomimetic design solutions.

biomimicry↗
NASA NTRSDate not supplied

LLMs and GenAI Tools to Depict Contributions of Human Systems to Spaceflight Tasks Execution

Recent advancements in Artificial Intelligence and Machine Learning (AI/ML) technologies, particularly Large Language Models (LLMs) capable of sophisticated syntax analysis, offer substantial potential in automating complex processes, thereby saving time and human resources. This study explores the development of an LLM-driven model designed to analyze and categorize a diverse set of Mars mission tasks into 18 predefined Human System Task Categories (HSTCs) based on their textual descriptions. As part of developing the Crew Health and Performance – Probabilistic Risk Assessment (CHP-PRA projects Performance Risk Model (PRisM) proof-of-concept, we established a framework to project performance scores from small-scale tests onto a preliminary list of Mars tasks. The foundation of our model was a comprehensive spreadsheet populated by NASA experts and clinicians, which detailed each Mars task alongside binary indicators of HSTC involvement. This dataset enabled the initial application of supervised ML, training and testing on existing HSTC labels. The HSTCs were originally defined from a medical system perspective, focusing on task impairments due to deteriorated human health. To expand our model's scope to include categories impacting performance, we face the challenge of generating binary labels (0 or 1) for new categories without pre-existing data. We address this by employing Generative AI (GenAI) software to determine whether a given task involved a new category by asking, "Does task A involve using category B?" We validate our approach by comparing the GenAI's binary classifications with the expert-provided labels for existing HSTCs. Notably, we utilize Ollama [4], a locally hosted GenAI tool that does not require cloud access, thus safeguarding NASA's proprietary data from unauthorized exposure. This study demonstrates the feasibility of leveraging cutting-edge AI tools to advance research, paving the way for automation and rapid decision-making in space exploration.

Mona Matar↗
NASA NTRSDate not supplied

Artificial Intelligence (AI) Methods for Automating the Impact Tool Evidence Library

INTRODUCTION: The development of the Evidence Library for use with the IMPACT (Informing Mission Planning via Analysis of Complex Tradespaces) probability risk assessment tool involved a multilayered, time intensive process of data collection and analysis by subject matter experts from the Exploration Medical Capability (ExMC) Element Clinical and Science Team to produce clinical findings forms (CliFFs) for 120 medical conditions. Artificial Intelligence Large Language Models (LLMs) can be leveraged to facilitate this process, thus reducing labor and time. TOPIC: CliFFs contain information about medical conditions as they pertain to spaceflight. This includes condition definitions, incidence data, crew task impairment estimates caused by conditions, treatment protocols and references to literature used for gathering condition evidence. Guided by the Evidence Library Methods document and the CliFF development instructions, a team has leveraged Microsoft Azure AI services and open-source documentation to construct an AI-assisted automated pipeline for CliFF development. This process is designed to search, retrieve, and evaluate the applicable data, and ultimately generate a completed CliFF. The LLM evaluates the relevance of each of the source materials to spaceflight, either as direct evidence or as an analog. The model extracts keywords and generates brief summaries to enhance search and retrieval in later stages of CliFF development. For instance, it can calculate epidemiological statistical data, such as incidence rates and the likelihood of best or worst-case scenarios. APPLICATION: Large Language Models (LLMs) can efficiently summarize large amounts of text. Leveraging this technology will automate data retrieval and evidence gathering for medical databases, like the IMPACT tool, by aiding in the labor-intensive process of analyzing large bodies of literature and organizing it into a formatted document like a CliFF. This added efficiency will enable expeditious expansion of the Evidence Library with additional medical conditions and update previous CLiFFs as new technology becomes available.

Ali Al↗
NASA NTRSDate not supplied

Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization

Recent Large Language Models (LLMs) have demonstrated impressive capabilities at tasks that require human intelligence and are a significant step towards human-like artificial intelligence (AI). Yet the performance of LLMs at reasoning tasks have been subpar and the reasoning capability of LLMs is a matter of significant debate. While it has been shown that the choice of the prompting technique to the LLM can alter its performance on a multitude of tasks, including reasoning, the best performing techniques require human-made prompts with the knowledge of the tasks at hand. We introduce a framework for what we call Combinatorial Reasoning (CR), a fully-automated prompting method, where reasons are sampled from an LLM pipeline and mapped into a Quadratic Unconstrained Binary Optimization (QUBO) problem. The framework investigates whether QUBO solutions can be profitably used to select a useful subset of the reasons to construct a Chain-of-Thought style prompt. We explore the acceleration of CR with specialized solvers. We also investigate the performance of simpler zero-shot strategies such as linear majority rule or random selection of reasons. Our preliminary study indicates that coupling a combinatorial solver to generative AI pipelines is an interesting avenue for AI reasoning and elucidates design principles for future CR methods.

combinatorial reasoning↗
NASA NTRSDate not supplied

Identifying Human Errors and Error Mechanisms From Accident Reports Using Large Language Models

Emerging operational concepts for aviation hinge on novel paradigms for human machine interaction. Critical to their safe operation is early consideration of human error into the design process. Existing methods for consideration of human error require significant expert input, which is challenging both in early design and in novel systems for which there is little existing safety expertise. In this research, we propose a methodology for identifying human error, error producing factors, and mechanisms in early design from historical incident reports. Additionally, we hypothesize that cross-domain sharing of lessons learned can aid with early design human considerations in circumstances where data is not relevant or incomplete. This is addressed by identifying causes of human error in aviation and railway domains through applying state-of-the art natural language processing techniques to historical incident reports. Using this method, it is possible to extract extensive reports on human error from past incidents. Using the proposed approach, we identify nine human errors from railway reports and fourteen from aviation reports, with three errors common to both domains. There is at least one error producing conditions for each human error while a majority of the errors have more than one error mechanism. We also found that a majority of the human errors, error producing factors, and error mechanisms (even if they are not common between the domains) can be used to inform safe operations across domains as long as the errors are not domain specific and are interpreted and contextualized using engineering judgement.

Human Errors↗