@inproceedings{zhang-etal-2026-multi-malls,
title = "Multi-{MALLS}: A Multilingual Benchmark for Natural Language to First-Order Logic Translation",
author = "Zhang, Haodi and
Wu, Xuefeng and
Wen, Jiawei and
Wang, Yichi and
Zhang, Liang-Jie and
Fan, Tao and
Song, Yuanfeng",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.94/",
pages = "1933--1950",
ISBN = "979-8-89176-462-0",
abstract = "Translating natural language to First-Order Logic (NL2FOL) is crucial for logic-based reasoning, but most existing models and benchmarks focus on English, leaving cross-lingual generalization underexplored. In this study, we present the first comprehensive investigation of cross-lingual robustness in NL2FOL. To support this, we introduce Multi-MALLS, the first multilingual benchmark for NL2FOL, which extends the widely-used MALLS dataset with high-quality translations into multiple languages. Using Multi-MALLS, we observe that state-of-the-art models experience a significant performance drop when applied to non-English inputs, highlighting the lack of robustness. To address this, we propose MA-FOL, a multi-agent framework that improves generalization without requiring any training on target languages. By decomposing the task into three modules, a language-agnostic structure generator, a language-specific predicate combiner, and a refinement component, MA-FOL achieves robust zero-shot generalization across diverse linguistic inputs. Additionally, we show that traditional evaluation metrics, such as Exact Match, often fail to assess semantic correctness. To remedy this, we introduce large language models (LLMs)-Judged Semantic Equivalence (SE), a new metric that leverages LLMs to evaluate whether generated formulas preserve the intended meaning. Extensive experiments demonstrate that MA-FOL outperforms strong baselines on Multi-MALLS, without any multilingual fine-tuning. The SE metric further reveals semantic correctness that traditional metrics miss. Overall, our work provides a benchmark to test robustness of NL2FOL, a framework to improve it, and a metric to evaluate it more effectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-multi-malls">
<titleInfo>
<title>Multi-MALLS: A Multilingual Benchmark for Natural Language to First-Order Logic Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haodi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuefeng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang-Jie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanfeng</namePart>
<namePart type="family">Song</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>Translating natural language to First-Order Logic (NL2FOL) is crucial for logic-based reasoning, but most existing models and benchmarks focus on English, leaving cross-lingual generalization underexplored. In this study, we present the first comprehensive investigation of cross-lingual robustness in NL2FOL. To support this, we introduce Multi-MALLS, the first multilingual benchmark for NL2FOL, which extends the widely-used MALLS dataset with high-quality translations into multiple languages. Using Multi-MALLS, we observe that state-of-the-art models experience a significant performance drop when applied to non-English inputs, highlighting the lack of robustness. To address this, we propose MA-FOL, a multi-agent framework that improves generalization without requiring any training on target languages. By decomposing the task into three modules, a language-agnostic structure generator, a language-specific predicate combiner, and a refinement component, MA-FOL achieves robust zero-shot generalization across diverse linguistic inputs. Additionally, we show that traditional evaluation metrics, such as Exact Match, often fail to assess semantic correctness. To remedy this, we introduce large language models (LLMs)-Judged Semantic Equivalence (SE), a new metric that leverages LLMs to evaluate whether generated formulas preserve the intended meaning. Extensive experiments demonstrate that MA-FOL outperforms strong baselines on Multi-MALLS, without any multilingual fine-tuning. The SE metric further reveals semantic correctness that traditional metrics miss. Overall, our work provides a benchmark to test robustness of NL2FOL, a framework to improve it, and a metric to evaluate it more effectively.</abstract>
<identifier type="citekey">zhang-etal-2026-multi-malls</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.94/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1933</start>
<end>1950</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-MALLS: A Multilingual Benchmark for Natural Language to First-Order Logic Translation
%A Zhang, Haodi
%A Wu, Xuefeng
%A Wen, Jiawei
%A Wang, Yichi
%A Zhang, Liang-Jie
%A Fan, Tao
%A Song, Yuanfeng
%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 zhang-etal-2026-multi-malls
%X Translating natural language to First-Order Logic (NL2FOL) is crucial for logic-based reasoning, but most existing models and benchmarks focus on English, leaving cross-lingual generalization underexplored. In this study, we present the first comprehensive investigation of cross-lingual robustness in NL2FOL. To support this, we introduce Multi-MALLS, the first multilingual benchmark for NL2FOL, which extends the widely-used MALLS dataset with high-quality translations into multiple languages. Using Multi-MALLS, we observe that state-of-the-art models experience a significant performance drop when applied to non-English inputs, highlighting the lack of robustness. To address this, we propose MA-FOL, a multi-agent framework that improves generalization without requiring any training on target languages. By decomposing the task into three modules, a language-agnostic structure generator, a language-specific predicate combiner, and a refinement component, MA-FOL achieves robust zero-shot generalization across diverse linguistic inputs. Additionally, we show that traditional evaluation metrics, such as Exact Match, often fail to assess semantic correctness. To remedy this, we introduce large language models (LLMs)-Judged Semantic Equivalence (SE), a new metric that leverages LLMs to evaluate whether generated formulas preserve the intended meaning. Extensive experiments demonstrate that MA-FOL outperforms strong baselines on Multi-MALLS, without any multilingual fine-tuning. The SE metric further reveals semantic correctness that traditional metrics miss. Overall, our work provides a benchmark to test robustness of NL2FOL, a framework to improve it, and a metric to evaluate it more effectively.
%U https://aclanthology.org/2026.findings-emnlp.94/
%P 1933-1950
Markdown (Informal)
[Multi-MALLS: A Multilingual Benchmark for Natural Language to First-Order Logic Translation](https://aclanthology.org/2026.findings-emnlp.94/) (Zhang et al., Findings 2026)
ACL