Summary of Petkaz at Semeval-2024 Task 8: Can Linguistics Capture the Specifics Of Llm-generated Text?, by Kseniia Petukhova et al.
PetKaz at SemEval-2024 Task 8: Can Linguistics Capture the Specifics of LLM-generated Text?
by Kseniia Petukhova, Roman Kazakov, Ekaterina Kochmar
First submitted to arxiv on: 8 Apr 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 Our paper presents a submission to the SemEval-2024 Task 8, focusing on detecting machine-generated texts in English. We combine RoBERTa-base embeddings with diversity features and use a resampled training set. Our approach scores 12th out of 124 in the monolingual track (Subtask A) and demonstrates generalizability across unseen models and domains, achieving an accuracy of 0.91. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary We developed a way to detect machine-generated texts in English. We used RoBERTa-base, which is a type of AI model, along with other features that help us tell real text from fake text. Our method worked well and was good at detecting machine-generated texts even when we tested it on new models and domains. |
