<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2025-harnessing">
    <titleInfo>
        <title>Harnessing and Evaluating the Intrinsic Extrapolation Ability of Large Language Models for Vehicle Trajectory Prediction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jiawei</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yanjiao</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xun</namePart>
        <namePart type="family">Gong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tingting</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hong</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yunfeng</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Luis</namePart>
            <namePart type="family">Chiruzzo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alan</namePart>
            <namePart type="family">Ritter</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Albuquerque, New Mexico</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-189-6</identifier>
    </relatedItem>
    <abstract>Emergent abilities of large language models (LLMs) have significantly advanced their application in autonomous vehicle (AV) research. Safe integration of LLMs into vehicles, however, necessitates their thorough understanding of dynamic traffic environments. Towards this end, this study introduces a framework leveraging LLMs’ built-in extrapolation capabilities for vehicle trajectory prediction, thereby evaluating their comprehension of the evolution of traffic agents’ behaviors and interactions over time. The framework employs a traffic encoder to extract spatial-level scene features from agents’ observed trajectories to facilitate efficient scene representation. To focus on LLM’s innate capabilities, scene features are then converted into LLM-compatible tokens through a reprogramming adapter and finally decoded into predicted trajectories with a linear decoder. Experimental results quantitatively demonstrate the framework’s efficacy in enabling off-the-shelf, frozen LLMs to achieve competitive trajectory prediction performance, with qualitative analyses revealing their enhanced understanding of complex, multi-agent traffic scenarios.</abstract>
    <identifier type="citekey">liu-etal-2025-harnessing</identifier>
    <identifier type="doi">10.18653/v1/2025.naacl-long.223</identifier>
    <location>
        <url>https://aclanthology.org/2025.naacl-long.223/</url>
    </location>
    <part>
        <date>2025-04</date>
        <extent unit="page">
            <start>4379</start>
            <end>4391</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Harnessing and Evaluating the Intrinsic Extrapolation Ability of Large Language Models for Vehicle Trajectory Prediction
%A Liu, Jiawei
%A Liu, Yanjiao
%A Gong, Xun
%A Wang, Tingting
%A Chen, Hong
%A Hu, Yunfeng
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F liu-etal-2025-harnessing
%X Emergent abilities of large language models (LLMs) have significantly advanced their application in autonomous vehicle (AV) research. Safe integration of LLMs into vehicles, however, necessitates their thorough understanding of dynamic traffic environments. Towards this end, this study introduces a framework leveraging LLMs’ built-in extrapolation capabilities for vehicle trajectory prediction, thereby evaluating their comprehension of the evolution of traffic agents’ behaviors and interactions over time. The framework employs a traffic encoder to extract spatial-level scene features from agents’ observed trajectories to facilitate efficient scene representation. To focus on LLM’s innate capabilities, scene features are then converted into LLM-compatible tokens through a reprogramming adapter and finally decoded into predicted trajectories with a linear decoder. Experimental results quantitatively demonstrate the framework’s efficacy in enabling off-the-shelf, frozen LLMs to achieve competitive trajectory prediction performance, with qualitative analyses revealing their enhanced understanding of complex, multi-agent traffic scenarios.
%R 10.18653/v1/2025.naacl-long.223
%U https://aclanthology.org/2025.naacl-long.223/
%U https://doi.org/10.18653/v1/2025.naacl-long.223
%P 4379-4391

Markdown (Informal)

[Harnessing and Evaluating the Intrinsic Extrapolation Ability of Large Language Models for Vehicle Trajectory Prediction](https://aclanthology.org/2025.naacl-long.223/) (Liu et al., NAACL 2025)

• Harnessing and Evaluating the Intrinsic Extrapolation Ability of Large Language Models for Vehicle Trajectory Prediction (Liu et al., NAACL 2025)

ACL

• Jiawei Liu, Yanjiao Liu, Xun Gong, Tingting Wang, Hong Chen, and Yunfeng Hu. 2025. Harnessing and Evaluating the Intrinsic Extrapolation Ability of Large Language Models for Vehicle Trajectory Prediction. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 4379–4391, Albuquerque, New Mexico. Association for Computational Linguistics.