An empirical study distills a taxonomy of human factual errors from newspaper corrections and shows LLMs achieve only 52% F1 on detection.
Rojas-Barahona, Pei-Hao Su, David Vandyke, Tsung-Hsien Wen, and Steve Young
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
First systematic test shows activation steering robustness drops sharply (up to 64%) under adversarial input perturbations across multiple extraction methods, models, and personas.
citing papers explorer
-
An Empirical Analysis of Factual Errors in Human-Written Text and its Application
An empirical study distills a taxonomy of human factual errors from newspaper corrections and shows LLMs achieve only 52% F1 on detection.
-
Adversarial Robustness of Activation Steering in Large Language Models
First systematic test shows activation steering robustness drops sharply (up to 64%) under adversarial input perturbations across multiple extraction methods, models, and personas.