@inproceedings{kupfer-etal-2026-wwtc,
title = "{WWTC}@{U}ni{A} at {S}em{E}val-2026 Task 13: {BERT}-based Code Authorship Detection and Qualitative Analysis",
author = "Kupfer, Linda and
Hader, Lisa and
Jaumann, Christian and
Friedrich, Annemarie",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.298/",
pages = "2359--2375",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes our system for SemEval-2026 Task 13 on detecting machine-generated code. We fine-tune small encoder-only models for detecting human-written versus machine-generated code and for identifying which large language model (LLM) family was used to obtain code. We find that a strong, general-purpose model (ModernBERT) outperforms models specifically pre-trained for the code domain. In the official evaluation, our system ranks 5th on subtask B and 6th on subtask C. Our detailed analysis reveals that comments and other natural language text that is part of the code snippets provide valuable information for identifying the LLM family that generated it. Moreover, we show that the embeddings of our finetuned ModernBERT do not distinguish well between LLM families, but they cluster human-written code by programming language."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kupfer-etal-2026-wwtc">
<titleInfo>
<title>WWTC@UniA at SemEval-2026 Task 13: BERT-based Code Authorship Detection and Qualitative Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linda</namePart>
<namePart type="family">Kupfer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Hader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Jaumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>This paper describes our system for SemEval-2026 Task 13 on detecting machine-generated code. We fine-tune small encoder-only models for detecting human-written versus machine-generated code and for identifying which large language model (LLM) family was used to obtain code. We find that a strong, general-purpose model (ModernBERT) outperforms models specifically pre-trained for the code domain. In the official evaluation, our system ranks 5th on subtask B and 6th on subtask C. Our detailed analysis reveals that comments and other natural language text that is part of the code snippets provide valuable information for identifying the LLM family that generated it. Moreover, we show that the embeddings of our finetuned ModernBERT do not distinguish well between LLM families, but they cluster human-written code by programming language.</abstract>
<identifier type="citekey">kupfer-etal-2026-wwtc</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.298/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2359</start>
<end>2375</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WWTC@UniA at SemEval-2026 Task 13: BERT-based Code Authorship Detection and Qualitative Analysis
%A Kupfer, Linda
%A Hader, Lisa
%A Jaumann, Christian
%A Friedrich, Annemarie
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F kupfer-etal-2026-wwtc
%X This paper describes our system for SemEval-2026 Task 13 on detecting machine-generated code. We fine-tune small encoder-only models for detecting human-written versus machine-generated code and for identifying which large language model (LLM) family was used to obtain code. We find that a strong, general-purpose model (ModernBERT) outperforms models specifically pre-trained for the code domain. In the official evaluation, our system ranks 5th on subtask B and 6th on subtask C. Our detailed analysis reveals that comments and other natural language text that is part of the code snippets provide valuable information for identifying the LLM family that generated it. Moreover, we show that the embeddings of our finetuned ModernBERT do not distinguish well between LLM families, but they cluster human-written code by programming language.
%U https://aclanthology.org/2026.semeval-1.298/
%P 2359-2375
Markdown (Informal)
[WWTC@UniA at SemEval-2026 Task 13: BERT-based Code Authorship Detection and Qualitative Analysis](https://aclanthology.org/2026.semeval-1.298/) (Kupfer et al., SemEval 2026)
ACL