# Dream at SemEval-2026 Task 13: SALSA for Single-Pass Machine-Generated Code Detection

arXiv: https://arxiv.org/abs/2606.25102 · HTML: https://mlsanity.com/paper/2606.25102/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 13 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Builds on (most cited first, 7 of 7)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings](https://mlsanity.com/paper/2503.13733/) (2025)
- [textttDroid: A Resource Suite for AI-Generated Code Detection](https://mlsanity.com/paper/2507.10583/) (2025)
- [AICD Bench: A Challenging Benchmark for AI-Generated Code Detection](https://mlsanity.com/paper/2602.02079/) (2026)
- [Early Period of Training Impacts Adaptation for Out-of-Distribution Generalization: An Empirical Study](https://mlsanity.com/paper/2403.15210/) (2024)

## Abstract (arXiv)

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 F1 = 0.789 on the official leaderboard, substantially outperforming the CodeBERT baseline (F1 = 0.305).