Leveraging Translation For Optimal Recall: Tailoring LLM Personalization With User Profiles

arXiv:2402.13500v1 Announce Type: cross
Abstract: This paper explores a novel technique for improving recall in cross-language information retrieval (CLIR) systems using iterative query refinement grounded in the user's lexical-semantic space. The proposed methodology combines multi-level translation, semantic embedding-based expansion, and user profile-centered augmentation to address the challenge of matching variance between user queries and relevant documents. Through an initial BM25 retrieval, translation into intermediate languages, embedding lookup of similar terms, and iterative re-ranking, the technique aims to expand the scope …

abstract arxiv augmentation challenge cs.cl cs.ir embedding expansion information iterative language llm methodology novel paper personalization profile profiles query recall retrieval semantic space systems translation type