English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Pangram 4 Technical Report: State-of-the-Art AI Text Detection

Forum topic · 小凯 · 2026-07-31

Summary

This arXiv paper (2607.27183) introduces Pangram 4, the latest deep-learning-based AI-text classification model from Pangram Labs. The model achieves an AUROC of 0.9916 with a false positive rate of 0.0041% and a false negative rate of 0.3396%. Compared with its predecessor Pangram 3, Pangram 4 delivers higher overall accuracy, superior out-of-distribution generalization, and stronger robustness against adversarial attacks. A novel contribution is its improved ability to distinguish fine-grained edits and mixed AI-human co-authored text, with demonstrated improvements in boundary detection tasks and detection of interleaved AI assistance. Benchmarks on standard AI detection datasets show that Pangram 4 achieves state-of-the-art performance across a wide variety of settings and domains. Authors: Ben Glickenhaus, Katherine Thai, Jenna Russell, Elyas Masrour, Yue Han, Max Spero, and Bradley Emi. Published July 29, 2026.

Paper Overview

Field: NLP Authors: Ben Glickenhaus, Katherine Thai, Jenna Russell, Elyas Masrour, Yue Han, Max Spero, Bradley Emi Published: 2026-07-29 arXiv: 2607.27183

Summary

This paper presents Pangram 4, the latest deep-learning-based AI-text classification model from Pangram Labs. The authors achieve an AUROC of 0.9916 with a false positive rate of 0.0041% and a false negative rate of 0.3396%.

Key Contributions

  • Improved accuracy: Higher overall detection accuracy compared with Pangram 3.
  • Robustness: Superior out-of-distribution generalization and stronger resistance to adversarial attacks.
  • Fine-grained and mixed-text detection: A novel capability to distinguish fine-grained edits and mixed AI-human co-authored text, with improvements on both boundary detection tasks and detection of interleaved AI assistance.
  • State-of-the-art results: Metrics on standard AI detection benchmarks show Pangram 4 achieves state-of-the-art performance on the AI text detection task across a wide variety of settings and domains.

Original Abstract (excerpt)

> We present Pangram 4, the latest deep-learning-based AI-text classification model from Pangram Labs. We achieve an AUROC of 0.9916 with a false positive rate of 0.0041% and a false negative rate of 0.3396%. In addition to its increased overall accuracy compared with Pangram 3, Pangram 4 exhibits superior out-of-distribution generalization and adversarial attack robustness. Another novel contribution of Pangram 4 is its improved ability to distinguish fine-grained edits and mixed AI-human co-authored text. We demonstrate improvements to both boundary detection tasks and the detection of interleaved AI assistance. Finally, we report metrics on standard AI detection benchmarks showing that Pangram 4 achieves state-of-the-art performance on the AI text detection task across a wide variety of settings and domains.

Full paper: arXiv:2607.27183

--- *Auto-collected on 2026-07-31*

Tags

#ai-text-detection#nlp#arxiv#machine-learning#pangram#text-classification#llm

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178503825