<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ranaldi-etal-2026-surfacing">
    <titleInfo>
        <title>Surfacing Program Structure with Auxiliary Signals for Low-Resource Code Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Federico</namePart>
        <namePart type="family">Ranaldi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nickil</namePart>
        <namePart type="family">Maveli</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shay</namePart>
        <namePart type="given">B</namePart>
        <namePart type="family">Cohen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fabio</namePart>
        <namePart type="given">Massimo</namePart>
        <namePart type="family">Zanzotto</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>LLMs are extremely good code translators, except when it matters most: translating from low-resource to high-resource programming languages. The reason may lie in the fact that code translation relies on superficial lexical cues rather than on exploiting the deeper, language-agnostic program structure. We propose BoJac (Bohm–Jacopini), a novel commenting approach that pushes LLMs to exploit program structure by verbalizing structured programming principles in a guided natural language format. By using structure, BoJac enhances the ability to translate low-resource to-high-resource code. Using equivalent code benchmarks across multiple language pairs, we compare BoJac against several forms of auxIliary guidance provided alongside the source code: synthetic free-form chain-of comments, abstract syntax tree, and I/O Traces. To disentangle structural understanding from identifier-level matching, we repeat all experiments under name mangling and extend the same comparison to LoRA Fine-tuning on signal-augmented training sets. Our results show that the strongest gains come from auxiliary signals expressed in natural language, particularly when they explicitly encode structural and computational-level properties of the source code as in BoJac. While purely structural representations appear less effective, hybrid approaches such as BoJac, which convey structural and paradigm-level information through formalised natural language, emerge as a promising direction.</abstract>
    <identifier type="citekey">ranaldi-etal-2026-surfacing</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2234/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>50850</start>
            <end>50867</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Surfacing Program Structure with Auxiliary Signals for Low-Resource Code Translation
%A Ranaldi, Federico
%A Maveli, Nickil
%A Cohen, Shay B.
%A Zanzotto, Fabio Massimo
%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 ranaldi-etal-2026-surfacing
%X LLMs are extremely good code translators, except when it matters most: translating from low-resource to high-resource programming languages. The reason may lie in the fact that code translation relies on superficial lexical cues rather than on exploiting the deeper, language-agnostic program structure. We propose BoJac (Bohm–Jacopini), a novel commenting approach that pushes LLMs to exploit program structure by verbalizing structured programming principles in a guided natural language format. By using structure, BoJac enhances the ability to translate low-resource to-high-resource code. Using equivalent code benchmarks across multiple language pairs, we compare BoJac against several forms of auxIliary guidance provided alongside the source code: synthetic free-form chain-of comments, abstract syntax tree, and I/O Traces. To disentangle structural understanding from identifier-level matching, we repeat all experiments under name mangling and extend the same comparison to LoRA Fine-tuning on signal-augmented training sets. Our results show that the strongest gains come from auxiliary signals expressed in natural language, particularly when they explicitly encode structural and computational-level properties of the source code as in BoJac. While purely structural representations appear less effective, hybrid approaches such as BoJac, which convey structural and paradigm-level information through formalised natural language, emerge as a promising direction.
%U https://aclanthology.org/2026.emnlp-main.2234/
%P 50850-50867

Markdown (Informal)

[Surfacing Program Structure with Auxiliary Signals for Low-Resource Code Translation](https://aclanthology.org/2026.emnlp-main.2234/) (Ranaldi et al., EMNLP 2026)

• Surfacing Program Structure with Auxiliary Signals for Low-Resource Code Translation (Ranaldi et al., EMNLP 2026)

ACL

• Federico Ranaldi, Nickil Maveli, Shay B. Cohen, and Fabio Massimo Zanzotto. 2026. Surfacing Program Structure with Auxiliary Signals for Low-Resource Code Translation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 50850–50867, Budapest, Hungary. Association for Computational Linguistics.