GPT-3 shows that scaling an autoregressive language model to 175 billion parameters enables strong few-shot performance across diverse NLP tasks via in-context prompting without fine-tuning.
Automatic detection of generated text is easiest when humans are fooled
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Recursive paraphrasing attacks substantially lower detection rates for multiple AI text detectors with only minor quality loss, while a theoretical analysis ties best-case AUROC to total variation distance between human and AI distributions.
Detector proxy analysis of real repositories finds LLM-like code decreasing over time and common in tests, with more in company repos, substantial clones, stable but often ungrammatical comments, and few linked bugs.
Keystroke dynamics models outperform text-only detectors for spotting LLM-assisted academic dishonesty in practical scenarios, though performance drops under adversarial conditions.
Shared task findings show near-perfect binary detection of AI-generated text but greater difficulty in attributing outputs to particular language models.
citing papers explorer
-
Language Models are Few-Shot Learners
GPT-3 shows that scaling an autoregressive language model to 175 billion parameters enables strong few-shot performance across diverse NLP tasks via in-context prompting without fine-tuning.
-
Can AI-Generated Text be Reliably Detected?
Recursive paraphrasing attacks substantially lower detection rates for multiple AI text detectors with only minor quality loss, while a theoretical analysis ties best-case AUROC to total variation distance between human and AI distributions.
-
An Exploratory Study on LLM-Generated Code and Comments in Code Repositories
Detector proxy analysis of real repositories finds LLM-like code decreasing over time and common in tests, with more in company repos, substantial clones, stable but often ungrammatical comments, and few linked bugs.
-
Detecting LLM-Assisted Academic Dishonesty using Keystroke Dynamics
Keystroke dynamics models outperform text-only detectors for spotting LLM-assisted academic dishonesty in practical scenarios, though performance drops under adversarial conditions.
-
Findings of the Counter Turing Test: AI-Generated Text Detection
Shared task findings show near-perfect binary detection of AI-generated text but greater difficulty in attributing outputs to particular language models.