Summary of Enhancing Authorship Attribution Through Embedding Fusion: a Novel Approach with Masked and Encoder-decoder Language Models, by Arjun Ramesh Kaushik et al.
Enhancing Authorship Attribution through Embedding Fusion: A Novel Approach with Masked and Encoder-Decoder Language Models
by Arjun Ramesh Kaushik, Sunil Rufus R P, Nalini Ratha
First submitted to arxiv on: 1 Nov 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 The proposed framework uses textual embeddings from Pre-trained Language Models (PLMs) to reliably distinguish AI-generated and human-authored text. By integrating semantic information from multiple PLMs using Embedding Fusion, the approach harnesses their complementary strengths for enhanced performance. The evaluation across diverse datasets demonstrates strong performance, achieving classification accuracy above 96% and a Matthews Correlation Coefficient (MCC) above 0.93. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to tell AI-generated text from human-written text. It uses special language models called Pre-trained Language Models (PLMs) to create embeddings that capture the meaning of words. By combining these embeddings in a clever way, the approach can accurately identify AI-generated text and human-authored text. The results show that this method works well on different datasets, achieving high accuracy. |
Keywords
* Artificial intelligence * Classification * Embedding
