Technical Report on the Pangram AI-Generated Text Classifier (2024)
Pangram Text, a transformer-based neural network, distinguishes AI-generated text from human writing. It outperforms zero-shot methods like DetectGPT and leading commercial tools with over 38 times lower error rates across 10 text domains and 8 large language models. A novel training algorithm, hard negative mining with synthetic mirrors, drastically reduces false positives, and the classifier shows no bias against nonnative English speakers.
-->
[Submitted on 21 Feb 2024 (v1), last revised 29 Jul 2024 (this version, v3)]
Title:Technical Report on the Pangram AI-Generated Text Classifier
View a PDF of the paper titled Technical Report on the Pangram AI-Generated Text Classifier, by Bradley Emi and Max Spero
View PDF HTML (experimental)
Abstract:We present Pangram Text, a transformer-based neural network trained to distinguish text written by large language models from text written by humans. Pangram Text outperforms zero-shot methods such as DetectGPT as well as leading commercial AI detection tools with over 38 times lower error rates on a comprehensive benchmark comprised of 10 text domains (student writing, creative writing, scientific writing, books, encyclopedias, news, email, scientific papers, short-form Q&A) and 8 open- and closed-source large language models. We propose a training algorithm, hard negative mining with synthetic mirrors, that enables our classifier to achieve orders of magnitude lower false positive rates on high-data domains such as reviews. Finally, we show that Pangram Text is not biased against nonnative English speakers and generalizes to domains and models unseen during training.
Subjects:
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
MSC classes: 68T50
ACM classes: I.2.7
Cite as: arXiv:2402.14873 [cs.CL]
(or arXiv:2402.14873v3 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2402.14873
arXiv-issued DOI via DataCite
Submission history
From: Maxwell Spero [view email] [v1] Wed, 21 Feb 2024 17:13:41 UTC (416 KB)
[v2] Mon, 26 Feb 2024 05:28:41 UTC (418 KB)
[v3] Mon, 29 Jul 2024 08:27:34 UTC (309 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Technical Report on the Pangram AI-Generated Text Classifier, by Bradley Emi and Max Spero
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new | recent | 2024-02
Change to browse by:
cs cs.AI
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)