@inproceedings{sibuet-ruiz-etal-2026-mioffan,
title = "{M}io{FFA}n: An Annotation Software for Formula Formalization with {LLM} Automation Capabilities",
author = "Sibuet Ruiz, Nicolas and
Saggion, Horacio and
Rossi, Riccardo",
editor = "Rehm, Georg and
Dietze, Stefan and
Dessi, Danilo and
Maynard, Diana and
Schimmler, Sonja",
booktitle = "Proceedings of Natural Scientific Language Processing ({NSLP}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nslp-1.20/",
doi = "10.63317/4s56b6f4i3u9",
pages = "206--217",
abstract = "The automatic translation of mathematical expressions in scientific literature into executable symbolic code{---}a process we refer to as Formula Formalization{---}is hindered by a severe scarcity of high-quality, ground-truth datasets specialized for technical scientific domains. In this paper, we present MioFFAn, an open-source, document-centric, and customizable framework designed to facilitate rapid annotation for this task. Building upon the MioGatto architecture, we extend existing features to overcome structural limitations and pivot its scope by introducing specific functionalities for Formula Formalization, such as selection of equations of interest and aided symbolic code specification. By allowing users to configure custom taxonomies and properties for identified symbols, and compatible symbolic operators, we ensure the framework is adaptable to diverse specialized scientific fields. Furthermore, MioFFAn is designed to incorporate partial automation via Large Language Models. By defining a modular set of automated sub-tasks with strict output formats, we enable researchers to iteratively refine automation capabilities and evaluate competing strategies using standard NLP metrics. We specify the current automation methodology and perform a preliminary evaluation that demonstrates to efficacy of this human-in-the-loop approach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sibuet-ruiz-etal-2026-mioffan">
<titleInfo>
<title>MioFFAn: An Annotation Software for Formula Formalization with LLM Automation Capabilities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Sibuet Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horacio</namePart>
<namePart type="family">Saggion</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riccardo</namePart>
<namePart type="family">Rossi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Dietze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danilo</namePart>
<namePart type="family">Dessi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Maynard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonja</namePart>
<namePart type="family">Schimmler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The automatic translation of mathematical expressions in scientific literature into executable symbolic code—a process we refer to as Formula Formalization—is hindered by a severe scarcity of high-quality, ground-truth datasets specialized for technical scientific domains. In this paper, we present MioFFAn, an open-source, document-centric, and customizable framework designed to facilitate rapid annotation for this task. Building upon the MioGatto architecture, we extend existing features to overcome structural limitations and pivot its scope by introducing specific functionalities for Formula Formalization, such as selection of equations of interest and aided symbolic code specification. By allowing users to configure custom taxonomies and properties for identified symbols, and compatible symbolic operators, we ensure the framework is adaptable to diverse specialized scientific fields. Furthermore, MioFFAn is designed to incorporate partial automation via Large Language Models. By defining a modular set of automated sub-tasks with strict output formats, we enable researchers to iteratively refine automation capabilities and evaluate competing strategies using standard NLP metrics. We specify the current automation methodology and perform a preliminary evaluation that demonstrates to efficacy of this human-in-the-loop approach.</abstract>
<identifier type="citekey">sibuet-ruiz-etal-2026-mioffan</identifier>
<identifier type="doi">10.63317/4s56b6f4i3u9</identifier>
<location>
<url>https://aclanthology.org/2026.nslp-1.20/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>206</start>
<end>217</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MioFFAn: An Annotation Software for Formula Formalization with LLM Automation Capabilities
%A Sibuet Ruiz, Nicolas
%A Saggion, Horacio
%A Rossi, Riccardo
%Y Rehm, Georg
%Y Dietze, Stefan
%Y Dessi, Danilo
%Y Maynard, Diana
%Y Schimmler, Sonja
%S Proceedings of Natural Scientific Language Processing (NSLP) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F sibuet-ruiz-etal-2026-mioffan
%X The automatic translation of mathematical expressions in scientific literature into executable symbolic code—a process we refer to as Formula Formalization—is hindered by a severe scarcity of high-quality, ground-truth datasets specialized for technical scientific domains. In this paper, we present MioFFAn, an open-source, document-centric, and customizable framework designed to facilitate rapid annotation for this task. Building upon the MioGatto architecture, we extend existing features to overcome structural limitations and pivot its scope by introducing specific functionalities for Formula Formalization, such as selection of equations of interest and aided symbolic code specification. By allowing users to configure custom taxonomies and properties for identified symbols, and compatible symbolic operators, we ensure the framework is adaptable to diverse specialized scientific fields. Furthermore, MioFFAn is designed to incorporate partial automation via Large Language Models. By defining a modular set of automated sub-tasks with strict output formats, we enable researchers to iteratively refine automation capabilities and evaluate competing strategies using standard NLP metrics. We specify the current automation methodology and perform a preliminary evaluation that demonstrates to efficacy of this human-in-the-loop approach.
%R 10.63317/4s56b6f4i3u9
%U https://aclanthology.org/2026.nslp-1.20/
%U https://doi.org/10.63317/4s56b6f4i3u9
%P 206-217
Markdown (Informal)
[MioFFAn: An Annotation Software for Formula Formalization with LLM Automation Capabilities](https://aclanthology.org/2026.nslp-1.20/) (Sibuet Ruiz et al., NSLP 2026)
ACL