A RAG-and-DPO trained language model that generates whole query-completion lists improved production QAC in a live test (5.44% fewer keystrokes, 3.46% more adoptions), but the offline metrics reuse the training verifiers.
Title resolution pending
1 Pith paper cite this work, alongside 42 external citations. Polarity classification is still indexing.
1
Pith paper citing it
42
external citations · OpenAlex
fields
cs.IR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unifying Ranking and Generation in Query Auto-Completion via Retrieval-Augmented Generation and Multi-Objective Alignment
A RAG-and-DPO trained language model that generates whole query-completion lists improved production QAC in a live test (5.44% fewer keystrokes, 3.46% more adoptions), but the offline metrics reuse the training verifiers.