The first SoK on LLM-based AutoPT frameworks provides a six-dimension taxonomy of agent designs and a unified empirical benchmark evaluating 15 frameworks via over 10 billion tokens and 1,500 manually reviewed logs.
Survey of hallucination in natural language generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A four-module, discipline-agnostic course on AI-assisted literature review produces large self-reported confidence gains in hallucination detection, responsible use, and AI attribution.
citing papers explorer
-
Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing
The first SoK on LLM-based AutoPT frameworks provides a six-dimension taxonomy of agent designs and a unified empirical benchmark evaluating 15 frameworks via over 10 billion tokens and 1,500 manually reviewed logs.
-
A Discipline-Agnostic AI Literacy Course for Academic Research: Architecture, Pedagogy, and Implementation
A four-module, discipline-agnostic course on AI-assisted literature review produces large self-reported confidence gains in hallucination detection, responsible use, and AI attribution.