FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals

• URL: http://arxiv.org/abs/2605.04157v1
• Date: Tue, 05 May 2026 18:00:19 GMT
• Title: FMI_SU_Yotkova_Kastreva at SemEval-2026 Task 13: Lightweight Detection of LLM-Generated Code via Stylometric Signals
• Abstract summary: SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios.<n>This paper describes our participation in Subtask A (binary classification) and explores both pretrained code encoders and lightweight feature-based methods.
• Score: 42.82186147670303
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: SemEval-2026 Task 13 investigates machine-generated code detection across multiple programming languages and application scenarios, asking participating systems to generalize to unseen languages and domains. This paper describes our participation in Subtask A (binary classification) and explores both pretrained code encoders and lightweight feature-based methods. We design ratio-based features that are less sensitive to snippet length. To support the extraction of descriptiveness-related signals, we use parsing engines and a programming-language classifier. Additionally, we train a separate code-vs-text line classifier to identify raw natural language segments embedded within samples. We combine a shallow decision tree with heuristic rules derived from data analysis to produce the final predictions. Our approach is computationally efficient, requires only CPU resources for training, and achieves near-instant inference time, offering a lightweight alternative to large pretrained models.

Related papers

• Semantic Source Code Segmentation using Small and Large Language Models [2.5748316361772963]
  This paper introduces an automated, domain-specific approach for research R code segmentation using Large and Small Language Models (LLMs/SLMs)<n>We explore two distinct approaches: line-by-line analysis with context and range-based segment determination.<n>Our results show that context-based line-by-line analysis is superior over range-based segmentation.
  arXiv  Detail & Related papers  (2025-07-11T19:49:59Z)
• Zero-Shot Detection of LLM-Generated Code via Approximated Task Conditioning [8.571111167616165]
  Large Language Model (LLM)-generated code is a growing challenge with implications for security, intellectual property, and academic integrity.<n>We investigate the role of conditional probability distributions in improving zero-shot LLM-generated code detection.<n>We propose a novel zero-shot detection approach that approximates the original task used to generate a given code snippet.
  arXiv  Detail & Related papers  (2025-06-06T13:23:37Z)
• Training Neural Networks as Recognizers of Formal Languages [87.06906286950438]
  We train and evaluate neural networks directly as binary classifiers of strings.<n>We provide results on a variety of languages across the Chomsky hierarchy for three neural architectures.<n>Our contributions will facilitate theoretically sound empirical testing of language recognition claims in future work.
  arXiv  Detail & Related papers  (2024-11-11T16:33:25Z)
• From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models [63.188607839223046]
  This survey focuses on the benefits of scaling compute during inference. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation.
  arXiv  Detail & Related papers  (2024-06-24T17:45:59Z)
• Adaptable and Reliable Text Classification using Large Language Models [7.962669028039958]
  This paper introduces an adaptable and reliable text classification paradigm, which leverages Large Language Models (LLMs)<n>We evaluated the performance of several LLMs, machine learning algorithms, and neural network-based architectures on four diverse datasets.<n>It is shown that the system's performance can be further enhanced through few-shot or fine-tuning strategies.
  arXiv  Detail & Related papers  (2024-05-17T04:05:05Z)
• SparseCoder: Identifier-Aware Sparse Transformer for File-Level Code Summarization [51.67317895094664]
  This paper studies file-level code summarization, which can assist programmers in understanding and maintaining large source code projects. We propose SparseCoder, an identifier-aware sparse transformer for effectively handling long code sequences.
  arXiv  Detail & Related papers  (2024-01-26T09:23:27Z)
• Exploring Large Language Models for Code Explanation [3.2570216147409514]
  Large Language Models (LLMs) have made remarkable strides in Natural Language Processing. This study specifically delves into the task of generating natural-language summaries for code snippets, using various LLMs.
  arXiv  Detail & Related papers  (2023-10-25T14:38:40Z)
• GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator [114.8954615026781]
  We propose a GAN-style model for encoder-decoder pre-training by introducing an auxiliary discriminator. GanLM is trained with two pre-training objectives: replaced token detection and replaced token denoising. Experiments in language generation benchmarks show that GanLM with the powerful language understanding capability outperforms various strong pre-trained language models.
  arXiv  Detail & Related papers  (2022-12-20T12:51:11Z)
• LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models [67.19124099815645]
  We propose a novel Language-Aware Soft Prompting (LASP) learning method to alleviate base class overfitting. LASP is inherently amenable to including, during training, virtual classes, i.e. class names for which no visual samples are available. LASP matches and surpasses, for the first time, the accuracy on novel classes obtained by hand-crafted prompts and CLIP for 8 out of 11 test datasets.
  arXiv  Detail & Related papers  (2022-10-03T17:56:35Z)
• A Hierarchical Model for Spoken Language Recognition [29.948719321162883]
  Spoken language recognition ( SLR) refers to the automatic process used to determine the language present in a speech sample. We propose a novel hierarchical approach were two PLDA models are trained, one to generate scores for clusters of highly related languages and a second one to generate scores conditional to each cluster. We show that this hierarchical approach consistently outperforms the non-hierarchical one for detection of highly related languages.
  arXiv  Detail & Related papers  (2022-01-04T22:10:36Z)
• Multimodal Representation for Neural Code Search [18.371048875103497]
  We introduce tree-serialization methods on a simplified form of AST and build the multimodal representation for the code data. Our results show that both our tree-serialized representations and multimodal learning model improve the performance of neural code search.
  arXiv  Detail & Related papers  (2021-07-02T12:08:19Z)
• Deep Graph Matching and Searching for Semantic Code Retrieval [76.51445515611469]
  We propose an end-to-end deep graph matching and searching model based on graph neural networks. We first represent both natural language query texts and programming language code snippets with the unified graph-structured data. In particular, DGMS not only captures more structural information for individual query texts or code snippets but also learns the fine-grained similarity between them.
  arXiv  Detail & Related papers  (2020-10-24T14:16:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.