<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2026-bass">
    <titleInfo>
        <title>BASS: Budget-Aware Structured Search for Text-to-SQL Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bin</namePart>
        <namePart type="family">Zheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zheng</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kefan</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lulu</namePart>
        <namePart type="family">Cui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Tang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zijun</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chen</namePart>
        <namePart type="family">Anlong</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>Text-to-SQL generation remains challenging for small and medium-sized language models, which must produce queries that are structurally valid, schema-grounded, and semantically faithful under limited inference budgets. Naive test-time scaling strategies, such as repeated sampling or unconstrained search, often spend budget on invalid, redundant, or semantically weak candidates. We present BASS, a Budget-Aware Structured Search framework for Text-to-SQL generation. BASS searches over deterministic SQL semantic units produced by rule-based Structural Boundary Detection, with lightweight admissibility filtering to reject malformed units. It scores completed candidates using an execution-gated rubric verifier: non-executable SQL receives zero reward, while executable SQL is assigned a continuous semantic score based on schema grounding, intent matching, predicate correctness, aggregation and ordering, and join/compositional structure. To improve budget usage, BASS introduces stagnation-aware branch suppression and exhaustion-aware early stopping, reallocating computation away from saturated search regions. Experiments on Spider and BIRD show strong zero-shot performance across Qwen2.5-Coder backbones. Controlled analyses further show that BASS uses fixed maximum rollout budgets adaptively, achieves better quality–cost behavior than naive repeated sampling, and benefits from semantic verification and stagnation-aware budget control.</abstract>
    <identifier type="citekey">zheng-etal-2026-bass</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1025/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>21659</start>
            <end>21686</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T BASS: Budget-Aware Structured Search for Text-to-SQL Generation
%A Zheng, Bin
%A Chen, Zheng
%A Chen, Kefan
%A Cui, Lulu
%A Tang, Hao
%A Xu, Zijun
%A Anlong, Chen
%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 zheng-etal-2026-bass
%X Text-to-SQL generation remains challenging for small and medium-sized language models, which must produce queries that are structurally valid, schema-grounded, and semantically faithful under limited inference budgets. Naive test-time scaling strategies, such as repeated sampling or unconstrained search, often spend budget on invalid, redundant, or semantically weak candidates. We present BASS, a Budget-Aware Structured Search framework for Text-to-SQL generation. BASS searches over deterministic SQL semantic units produced by rule-based Structural Boundary Detection, with lightweight admissibility filtering to reject malformed units. It scores completed candidates using an execution-gated rubric verifier: non-executable SQL receives zero reward, while executable SQL is assigned a continuous semantic score based on schema grounding, intent matching, predicate correctness, aggregation and ordering, and join/compositional structure. To improve budget usage, BASS introduces stagnation-aware branch suppression and exhaustion-aware early stopping, reallocating computation away from saturated search regions. Experiments on Spider and BIRD show strong zero-shot performance across Qwen2.5-Coder backbones. Controlled analyses further show that BASS uses fixed maximum rollout budgets adaptively, achieves better quality–cost behavior than naive repeated sampling, and benefits from semantic verification and stagnation-aware budget control.
%U https://aclanthology.org/2026.findings-emnlp.1025/
%P 21659-21686

Markdown (Informal)

[BASS: Budget-Aware Structured Search for Text-to-SQL Generation](https://aclanthology.org/2026.findings-emnlp.1025/) (Zheng et al., Findings 2026)

• BASS: Budget-Aware Structured Search for Text-to-SQL Generation (Zheng et al., Findings 2026)

ACL

• Bin Zheng, Zheng Chen, Kefan Chen, Lulu Cui, Hao Tang, Zijun Xu, and Chen Anlong. 2026. BASS: Budget-Aware Structured Search for Text-to-SQL Generation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 21659–21686, Budapest, Hungary. Association for Computational Linguistics.