Long-form factuality in large language models Jerry Wei 1 Chengrun Y ang 1 Xinying Song 1 Yifeng Lu

To benchmark a model's long-form factuality in open domains, we first use GPT -4 to generate LongFact, a prompt set comprising thousands of questions spanning 38 topics. We then propose that LLM agents can be used as automated evaluators for long-form factuality through a method which we call Search-Augmented Factuality Evaluator (SAFE).