<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-silence">
    <titleInfo>
        <title>Silence over Error: Risk-Averse Navigation Landmark Extraction via Progressive MLLM Alignment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xin</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziqi</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Changning</namePart>
        <namePart type="family">Shao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junhao</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fanxiang</namePart>
        <namePart type="family">Zeng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Existing pedestrian navigation systems often provide direction-only instructions with limited visual confirmation at complex intersections or along long straight paths. We study coordinate-free landmark extraction from dashcam image sequences. The model returns a set of landmarks with structured attributes (e.g., category and description), or abstains when visual evidence is insufficient. Although general MLLMs can recognize street-scene objects, they do not reliably follow expert rules for filtering ambiguous candidates. Moreover, a false landmark can mislead a pedestrian, making precision more important than exhaustive coverage in this task. We therefore develop a progressive alignment framework, supported by a landmark annotation and augmentation pipeline that converts navigation experts’ selection criteria into staged supervision signals. We further propose a hard-gated bipartite matcher for box-free evaluation and a navigation-aware risk-sensitive reward that penalizes false positives more heavily than abstentions without inducing blanket silence. On the held-out benchmark, our model achieves 92.29% precision while maintaining practical coverage, outperforming strong MLLM baselines. A 30-day A/B test with 2M users on the Amap platform further shows that landmark-augmented instructions reduce departure-confirmation latency by 23.5%. Together, these results demonstrate that risk-aware alignment enables reliable, abstention-capable landmark extraction for navigation.</abstract>
    <identifier type="citekey">yang-etal-2026-silence</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1478/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>31455</start>
            <end>31476</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Silence over Error: Risk-Averse Navigation Landmark Extraction via Progressive MLLM Alignment
%A Yang, Xin
%A Cao, Ziqi
%A Shao, Changning
%A Lin, Junhao
%A Zeng, Fanxiang
%A Liu, Yue
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F yang-etal-2026-silence
%X Existing pedestrian navigation systems often provide direction-only instructions with limited visual confirmation at complex intersections or along long straight paths. We study coordinate-free landmark extraction from dashcam image sequences. The model returns a set of landmarks with structured attributes (e.g., category and description), or abstains when visual evidence is insufficient. Although general MLLMs can recognize street-scene objects, they do not reliably follow expert rules for filtering ambiguous candidates. Moreover, a false landmark can mislead a pedestrian, making precision more important than exhaustive coverage in this task. We therefore develop a progressive alignment framework, supported by a landmark annotation and augmentation pipeline that converts navigation experts’ selection criteria into staged supervision signals. We further propose a hard-gated bipartite matcher for box-free evaluation and a navigation-aware risk-sensitive reward that penalizes false positives more heavily than abstentions without inducing blanket silence. On the held-out benchmark, our model achieves 92.29% precision while maintaining practical coverage, outperforming strong MLLM baselines. A 30-day A/B test with 2M users on the Amap platform further shows that landmark-augmented instructions reduce departure-confirmation latency by 23.5%. Together, these results demonstrate that risk-aware alignment enables reliable, abstention-capable landmark extraction for navigation.
%U https://aclanthology.org/2026.findings-emnlp.1478/
%P 31455-31476

Markdown (Informal)

[Silence over Error: Risk-Averse Navigation Landmark Extraction via Progressive MLLM Alignment](https://aclanthology.org/2026.findings-emnlp.1478/) (Yang et al., Findings 2026)

• Silence over Error: Risk-Averse Navigation Landmark Extraction via Progressive MLLM Alignment (Yang et al., Findings 2026)

ACL

• Xin Yang, Ziqi Cao, Changning Shao, Junhao Lin, Fanxiang Zeng, and Yue Liu. 2026. Silence over Error: Risk-Averse Navigation Landmark Extraction via Progressive MLLM Alignment. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 31455–31476, Budapest, Hungary. Association for Computational Linguistics.