@inproceedings{tuli-etal-2026-mindflayer-semeval,
    title = "{M}ind{F}layer at {S}em{E}val-2026 Task 13:{LACR}-{ENS}: Calibration-Aware Ensemble Routing for Cross-Language {AI}-Generated Code Detection",
    author = "Tuli, Jerin Romijah  and
      Naem, Talukder Naemul Hasan  and
      Pritom, Md. Sartaj Alam",
    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://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.294/",
    pages = "2322--2329",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper presents LACR-ENS, a calibration-aware ensemble system for detecting AI-generated code across eight programming languages (SemEval-2026 Task 13). We identify a severe asymmetric out-of-distribution (OOD) failure in fine-tuned code transformers: Expected Calibration Error doubles from 0.09 (seen languages) to 0.18 (unseen languages), and high-confidence predictions (p0.80) are wrong 39{\%} of the time on OOD inputs. We propose Language-Aware Confidence Routing (LACR), formally equivalent to implicit per-language temperature scaling, which reduces OOD ECE to 0.11 and improves macro-F1 by +0.013 over fixed-threshold ensembling. A language-family proximity analysis reveals that syntactic distance to training languages predicts OOD F1 with Pearson r=+0.94, providing a principled, label-free signal for deployment risk assessment and motivating a continuous routing extension. Our system combines UniXCoder and GraphCodeBERT via weighted logit-level fusion and achieves macro-F1 0.538 , outperforming comparable encoder-only systems. We additionally document a HuggingFace label inversion pitfall that suppressed our initial score by approximately 0.29 F1."
}