<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-liao-2026-ls">
    <titleInfo>
        <title>LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jinggui</namePart>
        <namePart type="family">Liang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lizi</namePart>
        <namePart type="family">Liao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-395-1</identifier>
    </relatedItem>
    <abstract>Large Language Models (LLMs) excel at diverse tasks, but remain vulnerable to malicious inputs such as jailbreak attacks. Current one-size-fits-all safety guardrails built from static datasets ignore each model’s unique safety profile and often force trade-offs between safety and utility. To address this gap, we propose LS-Guard, a framework for learning model-specific guardrails tailored to each LLM’s vulnerabilities. LS-Guard operates in two stages: First, it dynamically profiles a given LLM by probing it with malicious prompts to elicit the model’s responses, which are then dynamically labeled to reveal model-specific failure modes. Second, it uses this data to train a safety classifier with a collaborative multi-LoRA architecture. An orthogonality-constrained multi-task loss enables a central expert to learn general safety features while each subject-specific expert encodes the distinctive vulnerability patterns of one LLM. During inference, LS-Guard activates the central expert together with its model-specific expert to perform content moderation, yielding reliable safety decisions. Extensive experiments on multiple real-world LLMs demonstrate that LS-Guard significantly outperforms strong baseline guardrails, achieving superior robustness, adaptability, and generalization.</abstract>
    <identifier type="citekey">liang-liao-2026-ls</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-acl.989/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>19759</start>
            <end>19772</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs
%A Liang, Jinggui
%A Liao, Lizi
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F liang-liao-2026-ls
%X Large Language Models (LLMs) excel at diverse tasks, but remain vulnerable to malicious inputs such as jailbreak attacks. Current one-size-fits-all safety guardrails built from static datasets ignore each model’s unique safety profile and often force trade-offs between safety and utility. To address this gap, we propose LS-Guard, a framework for learning model-specific guardrails tailored to each LLM’s vulnerabilities. LS-Guard operates in two stages: First, it dynamically profiles a given LLM by probing it with malicious prompts to elicit the model’s responses, which are then dynamically labeled to reveal model-specific failure modes. Second, it uses this data to train a safety classifier with a collaborative multi-LoRA architecture. An orthogonality-constrained multi-task loss enables a central expert to learn general safety features while each subject-specific expert encodes the distinctive vulnerability patterns of one LLM. During inference, LS-Guard activates the central expert together with its model-specific expert to perform content moderation, yielding reliable safety decisions. Extensive experiments on multiple real-world LLMs demonstrate that LS-Guard significantly outperforms strong baseline guardrails, achieving superior robustness, adaptability, and generalization.
%U https://aclanthology.org/2026.findings-acl.989/
%P 19759-19772

Markdown (Informal)

[LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs](https://aclanthology.org/2026.findings-acl.989/) (Liang & Liao, Findings 2026)

• LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs (Liang & Liao, Findings 2026)

ACL

• Jinggui Liang and Lizi Liao. 2026. LS-Guard: Adaptive Safety Guardrails Tailored to Individual LLMs. In Findings of the Association for Computational Linguistics: ACL 2026, pages 19759–19772, San Diego, California, United States. Association for Computational Linguistics.