Summary of Jamdec: Unsupervised Authorship Obfuscation Using Constrained Decoding Over Small Language Models, by Jillian Fisher et al.
JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
by Jillian Fisher, Ximing Lu, Jaehun Jung, Liwei Jiang, Zaid Harchaoui, Yejin Choi
First submitted to arxiv on: 13 Feb 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 proposes an unsupervised approach to authorship obfuscation, aiming to protect online authorship identity and privacy. The method addresses unique challenges in this field, including lack of supervision data for diverse authorship and domains, and the need for sufficient revision beyond simple paraphrasing to effectively hide authorship while preserving content fluency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps keep people’s identities safe on the internet by making it harder to figure out who wrote something online. It uses special computer methods that don’t need training data, which is important because there are many different types of writing and domains. The goal is to make sure the writing stays clear and easy to understand while keeping the author’s identity hidden. |
Keywords
» Artificial intelligence » Unsupervised
