<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uddin-bauer-2026-conformal">
    <titleInfo>
        <title>Conformal LLM Routing with Distribution-Free Safety Guarantees</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Iqtedar</namePart>
        <namePart type="family">Uddin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">André</namePart>
        <namePart type="family">Bauer</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Santosh</namePart>
            <namePart type="family">T.Y.S.S.</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="given">Diego</namePart>
            <namePart type="family">Rodriguez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ona</namePart>
            <namePart type="family">de Gibert</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">979-8-89176-393-7</identifier>
    </relatedItem>
    <abstract>LLM routing directs queries to a cheaper model when it suffices and to an expensive model otherwise, reducing inference cost. Existing input-based routers optimize cost-performance trade-offs but provide no formal bound on how often the cheaper model fails among routed queries. We adapt a proactive conformal gate framework to LLM routing. A logistic regression gate trained on text embeddings predicts per-query safety, and Clopper-Pearson conformal calibration selects a routing threshold that guarantees the violation rate among routed queries stays below α (the violation tolerance) with probability at least 1 - δ (the confidence level). On two benchmarks covering math reasoning (GSM8K) and multi-domain knowledge (MMLU), routing between Mixtral-8x7B and GPT-4 (a 24.5\times cost difference), our method maintains the target α within the δ tolerance across a sweep from 0.05 to 0.50, while a validation-tuned baseline crosses the violation boundary on GSM8K. A feasibility analysis across all 10 RouterBench models reveals that routability is jointly model- and task-dependent. To our knowledge, this is the first input-based LLM router with distribution-free safety guarantees.</abstract>
    <identifier type="citekey">uddin-bauer-2026-conformal</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-srw.70/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>791</start>
            <end>799</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Conformal LLM Routing with Distribution-Free Safety Guarantees
%A Uddin, Iqtedar
%A Bauer, André
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F uddin-bauer-2026-conformal
%X LLM routing directs queries to a cheaper model when it suffices and to an expensive model otherwise, reducing inference cost. Existing input-based routers optimize cost-performance trade-offs but provide no formal bound on how often the cheaper model fails among routed queries. We adapt a proactive conformal gate framework to LLM routing. A logistic regression gate trained on text embeddings predicts per-query safety, and Clopper-Pearson conformal calibration selects a routing threshold that guarantees the violation rate among routed queries stays below α (the violation tolerance) with probability at least 1 - δ (the confidence level). On two benchmarks covering math reasoning (GSM8K) and multi-domain knowledge (MMLU), routing between Mixtral-8x7B and GPT-4 (a 24.5\times cost difference), our method maintains the target α within the δ tolerance across a sweep from 0.05 to 0.50, while a validation-tuned baseline crosses the violation boundary on GSM8K. A feasibility analysis across all 10 RouterBench models reveals that routability is jointly model- and task-dependent. To our knowledge, this is the first input-based LLM router with distribution-free safety guarantees.
%U https://aclanthology.org/2026.acl-srw.70/
%P 791-799

Markdown (Informal)

[Conformal LLM Routing with Distribution-Free Safety Guarantees](https://aclanthology.org/2026.acl-srw.70/) (Uddin & Bauer, ACL 2026)

• Conformal LLM Routing with Distribution-Free Safety Guarantees (Uddin & Bauer, ACL 2026)

ACL

• Iqtedar Uddin and André Bauer. 2026. Conformal LLM Routing with Distribution-Free Safety Guarantees. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 791–799, San Diego, California, United States. Association for Computational Linguistics.