Concept
Query2doc
An LLM-based query expansion method that expands query semantics by prompting a language model to generate relevant short passages from the original query, thereby improving recall in information retrieval.
Timeline (last 90 days)
Oct 12
SAFE-QE injects only 4.3 unsupported terms per query, compared to 27.8 for Query2doc and 57.5 for HyDE.
Unverified50%
Oct 12
Query2doc achieves LLM-based query expansion by generating short paragraphs, while HyDE does so by generating hypothetical documents.
Unverified50%