Retrieval · Evaluation

Evaluating Verifiability in Generative Search Engines

Free while signed in. Answers cite the passages they came from.

First page

The curator’s take

Audits popular generative search engines for citation accuracy.

Key points

Human evaluation: Performs rigorous human evaluation of Bing Chat, Perplexity AI, and NeevaAI responses.

Citation failure rate: Finds only 52% of generated sentences are supported by citations and only 75% of citations actually support the claim.

Verifiability gap: Reveals a significant gap between generative search engines' citation promises and their actual reliability.

Trust-in-AI research: Important empirical foundation for subsequent research on grounded generation and RAG accuracy.

Every Monday

The same picks and the same summaries, in your inbox. Free, and 176 issues deep.