AI-Generated Text Detection

Overview

The field studies how to identify whether text was generated or revised by language models, and sometimes which model or spans were involved. Methods range from supervised transformers and stylometric features to zero-shot likelihood, perplexity, token-pattern, and hidden-representation tests. Benchmarks increasingly test multiple languages, domains, generators, paraphrases, and mixed human–AI writing rather than only clean human-versus-machine examples. Detectors can perform strongly on familiar data, but distribution shifts, editing, and stylistic differences can cause missed detections or false accusations, leaving reliable use in high-stakes settings unresolved.

Latest papers

CardsList

185 papers16 papers in the last four weeks, down 41% on the four weeks before. 0.1% of all new papers.

  1. GPTZero: Robust Detection of LLM-Generated Texts

    Feb 13, 2026George Alexandru Adam, Alexander Cui, Edwin Thomas +9AI-Generated Text DetectionRobustness of Machine-Generated Text Detection

  2. Black-Box Detection of LLM-Generated Text Using Generalized Jensen-Shannon Divergence

    Oct 8, 2025Shuangyi Chen, Ashish KhistiAI-Generated Text DetectionLanguage Model Robustness

  3. VietBinoculars: A Zero-Shot Approach for Detecting Vietnamese LLM-Generated Text

    Sep 30, 2025Trieu Hai Nguyen, Sivaswamy AkileshAI-Generated Text DetectionLanguage Model Robustness

  4. Limits of LLM Text Detectors in Education

    Aug 11, 2025Lukas Gehring, Benjamin Paa\ssenLLM EvaluationAI-Generated Text Detection

  5. Robust and Fine-Grained Detection of AI Generated Texts

    Apr 16, 2025Ram Mohan Rao Kadiyala, Siddartha Pullakhandam, Kanwal Mehreen +12AI-Generated Text DetectionRobustness of Machine-Generated Text Detection