<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-emer">
    <titleInfo>
        <title>EMER-Guard: Protocol-Grounded Verification for LLM Emergency Instructions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zida</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guquan</namePart>
        <namePart type="family">You</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu</namePart>
        <namePart type="family">Zheng</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>When LLM-generated emergency advice becomes part of public-facing information infrastructure, aggregate accuracy is no longer an adequate safety target: missing a hazardous instruction and blocking a correct one impose different human costs. We study protocol-grounded verification, the post-hoc auditing of emergency instructions against authoritative guidance under asymmetric risk. We introduce EMER-GuardBench, a 69,000-example counterfactual benchmark plus a 1,000-example benign-stress set spanning 10 disaster scenarios and 6 hazard mechanisms, with instruction-group-disjoint splits and cited protocol evidence. We further propose EGIS, an evidence-conditioned, protocol-supervised verifier that jointly predicts hazard status, hazard mechanism, severity, evidence support, and counterfactual ranking. This establishes a protocol-conditioned task and protocol-supervised representation learning, not inference-time causal grounding. EGIS reaches 89.9 Harm F1 with 10.4% IID over-refusal and zero benign-stress false positives; across 364 LLM-judge operating points, none Pareto-dominates EGIS on Harm F1, over-refusal, and severity-weighted miss rate, and a 14.4×-larger Qwen3-8B+LoRA supervised baseline still trails under identical splits. Ablations show that evidence helps as training-time supervision rather than prompt decoration. Our Severity-Weighted Miss Rate exposes a tradeoff hidden by scalar safety scores: zero missed severity can be achieved by broad refusal. EMER-Guard reframes emergency LLM safety from advice generation to auditable, protocol-grounded, cost-sensitive verification.</abstract>
    <identifier type="citekey">yang-etal-2026-emer</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1205/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>27573</start>
            <end>27593</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T EMER-Guard: Protocol-Grounded Verification for LLM Emergency Instructions
%A Yang, Zida
%A You, Guquan
%A Zheng, Yu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yang-etal-2026-emer
%X When LLM-generated emergency advice becomes part of public-facing information infrastructure, aggregate accuracy is no longer an adequate safety target: missing a hazardous instruction and blocking a correct one impose different human costs. We study protocol-grounded verification, the post-hoc auditing of emergency instructions against authoritative guidance under asymmetric risk. We introduce EMER-GuardBench, a 69,000-example counterfactual benchmark plus a 1,000-example benign-stress set spanning 10 disaster scenarios and 6 hazard mechanisms, with instruction-group-disjoint splits and cited protocol evidence. We further propose EGIS, an evidence-conditioned, protocol-supervised verifier that jointly predicts hazard status, hazard mechanism, severity, evidence support, and counterfactual ranking. This establishes a protocol-conditioned task and protocol-supervised representation learning, not inference-time causal grounding. EGIS reaches 89.9 Harm F1 with 10.4% IID over-refusal and zero benign-stress false positives; across 364 LLM-judge operating points, none Pareto-dominates EGIS on Harm F1, over-refusal, and severity-weighted miss rate, and a 14.4×-larger Qwen3-8B+LoRA supervised baseline still trails under identical splits. Ablations show that evidence helps as training-time supervision rather than prompt decoration. Our Severity-Weighted Miss Rate exposes a tradeoff hidden by scalar safety scores: zero missed severity can be achieved by broad refusal. EMER-Guard reframes emergency LLM safety from advice generation to auditable, protocol-grounded, cost-sensitive verification.
%U https://aclanthology.org/2026.emnlp-main.1205/
%P 27573-27593

Markdown (Informal)

[EMER-Guard: Protocol-Grounded Verification for LLM Emergency Instructions](https://aclanthology.org/2026.emnlp-main.1205/) (Yang et al., EMNLP 2026)

• EMER-Guard: Protocol-Grounded Verification for LLM Emergency Instructions (Yang et al., EMNLP 2026)

ACL

• Zida Yang, Guquan You, and Yu Zheng. 2026. EMER-Guard: Protocol-Grounded Verification for LLM Emergency Instructions. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 27573–27593, Budapest, Hungary. Association for Computational Linguistics.