This paper describes AIpom, a system designed to detect a boundary between human-written and machine-generated text (SemEval-2024 Task 8, Subtask C: Human-Machine Mixed Text Detection). We propose a two-stage pipeline combining predictions from an instruction-tuned decoder-only model and encoder-only sequence taggers. AIpom is ranked second on the leaderboard while achieving a Mean Absolute Error of 15.94. Ablation studies confirm the benefits of pipelining encoder and decoder models, particularly in terms of improved performance.
@article{arxiv.2403.19354,
title = {AIpom at SemEval-2024 Task 8: Detecting AI-produced Outputs in M4},
author = {Alexander Shirnin and Nikita Andreev and Vladislav Mikhailov and Ekaterina Artemova},
journal= {arXiv preprint arXiv:2403.19354},
year = {2024}
}
Comments
2nd place at SemEval-2024 Task 8, Subtask C, to appear in SemEval-2024 proceedings