<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shihab-etal-2026-adaptive">
    <titleInfo>
        <title>Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ibne</namePart>
        <namePart type="given">Farabi</namePart>
        <namePart type="family">Shihab</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sanjeda</namePart>
        <namePart type="family">Akter</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anuj</namePart>
        <namePart type="family">Sharma</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 (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>Large language models increasingly require structured inference, from enforcing JSON schema to multilingual parsing, where outputs must satisfy complex constraints. We introduce MetaJuLS, a meta-reinforcement learning approach that learns universal constraint propagation policies applicable across languages and tasks without task-specific retraining. By formulating structured inference as adaptive constraint propagation and training a Graph Attention Network with meta-learning, MetaJuLS achieves 1.5-2.0× speedups over GPU-optimized baselines while maintaining an accuracy within 0.2% of that of state-of-the-art parsers. On Universal Dependencies across 10 languages and LLM-constrained generation (LogicBench, GSM8K-Constrained), MetaJuLS demonstrates rapid cross-domain adaptation: a policy trained on English parsing adapts to new languages and tasks with 5–10 gradient steps (5–15 seconds) rather than requiring hours of task-specific training. Mechanistic analysis reveals that the policy employs human-like parsing strategies (easy-first) and novel, non-intuitive heuristics. By reducing the number of propagation steps in LLM deployments, MetaJuLS contributes to Green AI by directly reducing the inference carbon footprint.</abstract>
    <identifier type="citekey">shihab-etal-2026-adaptive</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.701/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>15351</start>
            <end>15368</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning
%A Shihab, Ibne Farabi
%A Akter, Sanjeda
%A Sharma, Anuj
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F shihab-etal-2026-adaptive
%X Large language models increasingly require structured inference, from enforcing JSON schema to multilingual parsing, where outputs must satisfy complex constraints. We introduce MetaJuLS, a meta-reinforcement learning approach that learns universal constraint propagation policies applicable across languages and tasks without task-specific retraining. By formulating structured inference as adaptive constraint propagation and training a Graph Attention Network with meta-learning, MetaJuLS achieves 1.5-2.0× speedups over GPU-optimized baselines while maintaining an accuracy within 0.2% of that of state-of-the-art parsers. On Universal Dependencies across 10 languages and LLM-constrained generation (LogicBench, GSM8K-Constrained), MetaJuLS demonstrates rapid cross-domain adaptation: a policy trained on English parsing adapts to new languages and tasks with 5–10 gradient steps (5–15 seconds) rather than requiring hours of task-specific training. Mechanistic analysis reveals that the policy employs human-like parsing strategies (easy-first) and novel, non-intuitive heuristics. By reducing the number of propagation steps in LLM deployments, MetaJuLS contributes to Green AI by directly reducing the inference carbon footprint.
%U https://aclanthology.org/2026.acl-long.701/
%P 15351-15368

Markdown (Informal)

[Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning](https://aclanthology.org/2026.acl-long.701/) (Shihab et al., ACL 2026)

• Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning (Shihab et al., ACL 2026)

ACL

• Ibne Farabi Shihab, Sanjeda Akter, and Anuj Sharma. 2026. Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15351–15368, San Diego, California, United States. Association for Computational Linguistics.