Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection
Large language models have transformed code generation, raising concerns about authorship, assessment integrity, and software trust. SemEval-2026 Task 13 Subtask A defines detection as binary classification over code snippets, with emphasis on out-of-distribution generalization across unseen programming languages and domains. The authors propose SALSA (Single-pass Autoregressive LLM Structured Classification), which maps each class to a dedicated output token and trains the model to emit a single-token label. By combining balanced sampling, parameter-efficient fine-tuning, and conservative training, the system achieves OOD F1=0.789 on the official leaderboard, significantly outperforming the CodeBERT baseline (F1=0.305).
[2606.25102] Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection
[Submitted on 23 Jun 2026]
Title:Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection
View a PDF of the paper titled Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection, by Ruslan Berdichevsky and 1 other authors
View PDF HTML (experimental)
Abstract:Large language models have transformed code generation, raising concerns around authorship, assessment integrity, and software trust. SemEval-2026 Task 13 Subtask A operationalizes detection as binary classification over code snippets, with a particular emphasis on out-of-distribution (OOD) generalization across unseen programming languages and application domains. We propose a SALSA-style formulation, Single-pass Autoregressive LLM Structured Classification, that maps each class to a dedicated output token and trains the model to emit a single-token label in a structured response. Rather than engineering hand-crafted features or decision rules, this formulation delegates the authorship decision to the model. To improve OOD robustness, we combine balanced sampling across languages with parameter-efficient fine-tuning and conservative training (low learning rate, single epoch) to avoid overfitting to the training domain. Our best system achieves OOD $F_1 = 0.789$ on the official leaderboard, substantially outperforming the CodeBERT baseline ($F_1 = 0.305$).
Comments: Accepted to SemEval-2026, ACL 2026 workshop proceedings
Subjects:
Computation and Language (cs.CL)
Cite as: arXiv:2606.25102 [cs.CL]
(or arXiv:2606.25102v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2606.25102
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Ruslan Berdichevsky [view email] [v1] Tue, 23 Jun 2026 19:17:11 UTC (506 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection, by Ruslan Berdichevsky and 1 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)