Newest papers

From Tokens to Files: Multi-Granularity Detection and Localization of AI-Involved Code

Yue Xu, Xiyang Wang, Hui Liu, Bolei He · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27863 · cited by 0 works (OpenAlex) · open-access PDF

Japanese

コード生成のための大型言語モデルの使用率の増加により、人工知能関連コードから単に人間書かれたコードを区別する方法が求められています:ファイルでは、いくつかの部分がモデルによって生成され、あるいは本質的に変更されていても、いくつかのブロックがAIに関与している場合に、証拠を平均する、表面スタイリッシュな機能からグローバルコードの表示から、単一のスコアにファイルを圧縮する方法です。そのようなファイルを表記することにより、我々は、202線、ブロック、およびファイルレベルに属するトークンまたはブロックをローカル化することを目指しています。既存のアプローチでは、凍結されたコードモデルは、マシン書かれたファイル

Machine translation (Meta M2M100); the English original follows.

Abstract

The increasing use of large language models for code generation calls for methods that distinguish purely human-written code from AI-involved code: files in which any part, however small, was generated or substantially modified by a model. Beyond flagging such files, we aim to localize the lines or blocks attributable to AI. Existing approaches compress a file into a single score, from surface stylistic features or a global code representation, which averages away the evidence when only a few blocks are AI-involved. We propose a framework that models AI authorship at the token level and predicts at the line, block, and file levels. A frozen code language model is equipped with two low-rank adapters, trained separately on machine-written and human-written files; their per-token log-likelihood ratio provides local evidence of AI authorship. Lightweight heads aggregate this evidence within lines and blocks, using the surrounding code context, and their local predictions are aggregated into a file-level decision. We train on mixed-authorship files built from human originals and their AI-generated or AI-modified counterparts, including continuation and fill-in-the-middle scenarios. On an internal test set of 11,773 AI-involved files across six generation regimes against 2,541 human files, our method reaches 72.4 macro F1 at a 1% FPR operating point. With no adaptation, it reaches 62.5 line-level F1 on HybridCodeAuthorship, an external human-AI co-writing benchmark with no training split, above the 56 its own paper reports as the best line-level result. On 19,445 human-written files from repositories created before 2022, the false-positive rate stays between 0.55% and 0.81% under the transported 1% threshold, so the operating point holds on real human code.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Code (set theory), Flagging, Set (abstract data type), Language model, Benchmark (surveying)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange