protologue

Active Retrieval

Also called FLARE, forward-looking active retrieval.

Active retrieval augmented generation decides during generation when and what to retrieve; in FLARE, the model drafts the next sentence and, if it contains low-confidence tokens, uses that draft as a search query and regenerates the sentence with the retrieved evidence.

Description

Retrieving once before generation suits short answers but not long-form text whose information needs change as it is written. Triggering retrieval only on uncertainty limits extra calls to the points where the model is likely to be wrong.

Sources

  1. Jiang et al. (2023). Active Retrieval Augmented Generation.

Cite this entry

Protologue. (2026). Active Retrieval. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0136). https://protologue.com/t/active-retrieval/

BibTeX
@misc{protologue_active_retrieval,
  title = {Active Retrieval},
  author = {{Protologue}},
  year = {2026},
  howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.4.0},
  note = {Entry PTL-0136},
  url = {https://protologue.com/t/active-retrieval/}
}

Markdown JSON