<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="brunello-etal-2026-fixing">
    <titleInfo>
        <title>Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Andrea</namePart>
        <namePart type="family">Brunello</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cristian</namePart>
        <namePart type="family">Curaba</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Luca</namePart>
        <namePart type="family">Geatti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Michele</namePart>
        <namePart type="family">Mignani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Angelo</namePart>
        <namePart type="family">Montanari</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicola</namePart>
        <namePart type="family">Saccomanno</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), making the quality of NL-to-FOL benchmarks essential—yet these datasets have never been rigorously audited. Our first contribution is to present a systematic human inspection of the validation split of and a subset of test instances, finding that approximately 42.5% and 42% of entries, respectively, contain incorrect FOL formalizations (i.e., ground truth labels), with additional rates of ambiguous NL sentences (17.8% and 51%) and incorrect NLI labels in (8.4%). Our second contribution is to develop and release corrected ground truths for such datasets, showing that annotation errors distort model evaluation on a reference benchmark task: testing three state-of-the-art LLMs (Gemma 4 31B-it, Qwen3-30B-A3B, and GPT-4o-mini) with the corrected ground truths yields accuracy gains from +11 to +23 percentage points. Motivated by these findings, we propose an LLM based framework to support humans in manual reviewing NL-to-FOL datasets. By directing reviewers toward the most error-prone instances, we empirically show that it is possible to achieve 90% dataset accuracy after reviewing fewer than 20% of instances, compared to over 76% required by unguided review. We release all human-verified annotations and the code for our framework.</abstract>
    <identifier type="citekey">brunello-etal-2026-fixing</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.576/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>13195</start>
            <end>13220</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling
%A Brunello, Andrea
%A Curaba, Cristian
%A Geatti, Luca
%A Mignani, Michele
%A Montanari, Angelo
%A Saccomanno, Nicola
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F brunello-etal-2026-fixing
%X Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), making the quality of NL-to-FOL benchmarks essential—yet these datasets have never been rigorously audited. Our first contribution is to present a systematic human inspection of the validation split of and a subset of test instances, finding that approximately 42.5% and 42% of entries, respectively, contain incorrect FOL formalizations (i.e., ground truth labels), with additional rates of ambiguous NL sentences (17.8% and 51%) and incorrect NLI labels in (8.4%). Our second contribution is to develop and release corrected ground truths for such datasets, showing that annotation errors distort model evaluation on a reference benchmark task: testing three state-of-the-art LLMs (Gemma 4 31B-it, Qwen3-30B-A3B, and GPT-4o-mini) with the corrected ground truths yields accuracy gains from +11 to +23 percentage points. Motivated by these findings, we propose an LLM based framework to support humans in manual reviewing NL-to-FOL datasets. By directing reviewers toward the most error-prone instances, we empirically show that it is possible to achieve 90% dataset accuracy after reviewing fewer than 20% of instances, compared to over 76% required by unguided review. We release all human-verified annotations and the code for our framework.
%U https://aclanthology.org/2026.emnlp-main.576/
%P 13195-13220

Markdown (Informal)

[Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling](https://aclanthology.org/2026.emnlp-main.576/) (Brunello et al., EMNLP 2026)

• Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling (Brunello et al., EMNLP 2026)

ACL

• Andrea Brunello, Cristian Curaba, Luca Geatti, Michele Mignani, Angelo Montanari, and Nicola Saccomanno. 2026. Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 13195–13220, Budapest, Hungary. Association for Computational Linguistics.