@inproceedings{chauhan-nusrat-2026-ucsc,
title = "{UCSC}-{NLP} at {S}em{E}val-2026 Task 13: Multi-View Generalization and Diagnostic Analysis of Machine-Generated Code Detection",
author = "Chauhan, Kargi and
Nusrat, Sadiba",
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-1.311/",
pages = "2461--2468",
ISBN = "979-8-89176-414-9",
abstract = "This paper presents the system for SemEval-2026 Task 13, addressing both binary detection (Subtask A) and multi-class attribution (Subtask B). For Subtask A, we propose a robust multi-view training framework using UniXcoder-base, incorporating domain-specific structural prefixes, delexicalization with symmetric KL consistency loss, and token dropout. Our system achieves a high macro F1 of 0.845 on the out-of-distribution test set, demonstrating strong generalization across five unseen languages and two unseen domains. For Subtask B, we provide a rigorous diagnostic analysis of majority-class bias in transformer-based detectors. We reveal a significant performance gap where an 88.4{\%} accuracy masks a near-complete failure in minority-class attribution (0.086 Macro F1), highlighting that standard fine-tuning is insufficient for fine-grained generator identification. Our results expose distinct regimes in code detection and motivate the need for imbalance-aware, structure-focused modeling in future work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chauhan-nusrat-2026-ucsc">
<titleInfo>
<title>UCSC-NLP at SemEval-2026 Task 13: Multi-View Generalization and Diagnostic Analysis of Machine-Generated Code Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kargi</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadiba</namePart>
<namePart type="family">Nusrat</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 presents the system for SemEval-2026 Task 13, addressing both binary detection (Subtask A) and multi-class attribution (Subtask B). For Subtask A, we propose a robust multi-view training framework using UniXcoder-base, incorporating domain-specific structural prefixes, delexicalization with symmetric KL consistency loss, and token dropout. Our system achieves a high macro F1 of 0.845 on the out-of-distribution test set, demonstrating strong generalization across five unseen languages and two unseen domains. For Subtask B, we provide a rigorous diagnostic analysis of majority-class bias in transformer-based detectors. We reveal a significant performance gap where an 88.4% accuracy masks a near-complete failure in minority-class attribution (0.086 Macro F1), highlighting that standard fine-tuning is insufficient for fine-grained generator identification. Our results expose distinct regimes in code detection and motivate the need for imbalance-aware, structure-focused modeling in future work.</abstract>
<identifier type="citekey">chauhan-nusrat-2026-ucsc</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.311/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2461</start>
<end>2468</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UCSC-NLP at SemEval-2026 Task 13: Multi-View Generalization and Diagnostic Analysis of Machine-Generated Code Detection
%A Chauhan, Kargi
%A Nusrat, Sadiba
%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 chauhan-nusrat-2026-ucsc
%X This paper presents the system for SemEval-2026 Task 13, addressing both binary detection (Subtask A) and multi-class attribution (Subtask B). For Subtask A, we propose a robust multi-view training framework using UniXcoder-base, incorporating domain-specific structural prefixes, delexicalization with symmetric KL consistency loss, and token dropout. Our system achieves a high macro F1 of 0.845 on the out-of-distribution test set, demonstrating strong generalization across five unseen languages and two unseen domains. For Subtask B, we provide a rigorous diagnostic analysis of majority-class bias in transformer-based detectors. We reveal a significant performance gap where an 88.4% accuracy masks a near-complete failure in minority-class attribution (0.086 Macro F1), highlighting that standard fine-tuning is insufficient for fine-grained generator identification. Our results expose distinct regimes in code detection and motivate the need for imbalance-aware, structure-focused modeling in future work.
%U https://aclanthology.org/2026.semeval-1.311/
%P 2461-2468
Markdown (Informal)
[UCSC-NLP at SemEval-2026 Task 13: Multi-View Generalization and Diagnostic Analysis of Machine-Generated Code Detection](https://aclanthology.org/2026.semeval-1.311/) (Chauhan & Nusrat, SemEval 2026)
ACL