Summary of Deeppavlov at Semeval-2024 Task 8: Leveraging Transfer Learning For Detecting Boundaries Of Machine-generated Texts, by Anastasia Voznyuk and Vasily Konovalov
DeepPavlov at SemEval-2024 Task 8: Leveraging Transfer Learning for Detecting Boundaries of Machine-Generated Texts
by Anastasia Voznyuk, Vasily Konovalov
First submitted to arxiv on: 17 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a solution to the growing concern of misusing collaborative human-AI writing by developing a pipeline for augmenting data to detect the boundaries between human-written and machine-generated texts. Specifically, it focuses on fine-tuning DeBERTaV3 using supervised learning. The proposed approach achieves a new best Mean Absolute Error (MAE) score on the SemEval-2024 competition leaderboard. This advancement is crucial in identifying hybrid human-AI writing, which has become increasingly popular. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper aims to address the limitation of existing AI content detectors that often provide binary answers. Instead, it tackles the problem of detecting the boundaries between human-written and machine-generated texts, which is essential for nuanced applications. The proposed pipeline involves augmenting data for supervised fine-tuning of DeBERTaV3. |
Keywords
» Artificial intelligence » Fine tuning » Mae » Supervised
