AI search

Why citation-grounded answers matter more than fluent ones

Generated citations are the single biggest failure mode of AI in research. Here is how AI Search avoids them by retrieving first and writing second.

Last updated 29 May 2026 · 4 min read

A language model asked for references will happily invent them. The failure is not fixable by prompting; it is structural, because the model is completing text rather than looking anything up.

AI Search in SciExpert inverts the order. A query first hits the open OpenAlex scholarly index and retrieves real records with DOIs, titles, venues and years. Only then is a model asked to synthesise an answer, and only from the retrieved set.

The practical consequence is that every claim in the synthesis maps to a record you can open. If a claim has no source behind it, it does not appear.

This is slower than pure generation and that is the point. The value of a research tool is not fluency, it is that you can hand the output to a reviewer without apologising for it.

← All articles