<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-alba-2025-enabling">
    <titleInfo>
        <title>Enabling On-Premises Large Language Models for Space Traffic Management</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Enrique</namePart>
        <namePart type="family">De Alba</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Kunilovskaya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie</namePart>
            <namePart type="family">Escribe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Natural language processing systems leveraging on-premises large language models (LLMs) can translate natural language into structured JSON commands for Space Traffic Management (STM) systems. While cloud-based LLMs excel at this task, security constraints necessitate local deployment, requiring evaluation of smaller on-premises models. We demonstrate that resource-efficient 7B-parameter models can achieve high accuracy for STM command generation through a two-stage pipeline. Our pipeline first classifies objectives, then generates schemas. Empirically, we observe that initial classification accuracy strongly influences overall performance, with failures cascading to the generation stage. We demonstrate that quantization disproportionately increases structural errors compared to semantic errors across 405 objectives. The best quantized model (Falcon3-7B-GPTQ) shows a 3.45% accuracy drop, primarily from structural errors. Our findings highlight limitations in how model compression affects applications that require syntactic validity. More broadly, we explore the feasibility of LLM deployment in air-gapped environments while uncovering how quantization asymmetrically impacts structured output generation.</abstract>
    <identifier type="citekey">de-alba-2025-enabling</identifier>
    <location>
        <url>https://aclanthology.org/2025.ranlp-1.32/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>260</start>
            <end>267</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enabling On-Premises Large Language Models for Space Traffic Management
%A De Alba, Enrique
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F de-alba-2025-enabling
%X Natural language processing systems leveraging on-premises large language models (LLMs) can translate natural language into structured JSON commands for Space Traffic Management (STM) systems. While cloud-based LLMs excel at this task, security constraints necessitate local deployment, requiring evaluation of smaller on-premises models. We demonstrate that resource-efficient 7B-parameter models can achieve high accuracy for STM command generation through a two-stage pipeline. Our pipeline first classifies objectives, then generates schemas. Empirically, we observe that initial classification accuracy strongly influences overall performance, with failures cascading to the generation stage. We demonstrate that quantization disproportionately increases structural errors compared to semantic errors across 405 objectives. The best quantized model (Falcon3-7B-GPTQ) shows a 3.45% accuracy drop, primarily from structural errors. Our findings highlight limitations in how model compression affects applications that require syntactic validity. More broadly, we explore the feasibility of LLM deployment in air-gapped environments while uncovering how quantization asymmetrically impacts structured output generation.
%U https://aclanthology.org/2025.ranlp-1.32/
%P 260-267

Markdown (Informal)

[Enabling On-Premises Large Language Models for Space Traffic Management](https://aclanthology.org/2025.ranlp-1.32/) (De Alba, RANLP 2025)

• Enabling On-Premises Large Language Models for Space Traffic Management (De Alba, RANLP 2025)

ACL

• Enrique De Alba. 2025. Enabling On-Premises Large Language Models for Space Traffic Management. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 260–267, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.