Retrieving external knowledge is essential for solving real-world tasks, yet it remains challenging when the relationship between a query and its relevant knowledge involves implicit and complex reasoning beyond surface-level semantic or lexical matching
Shared by @ai-firehose.column.social ↗
arxiv.org1mo agoEvaluating the quality of search, ranking and RAG systems traditionally requires a significant number of human relevance annotations. In recent times, several deployed systems have explored the usage of Large Language Models (LLMs) as automated judges for
Shared by @ai-firehose.column.social ↗arxiv.org1mo agoRetrieval effectiveness varies substantially across queries, making it important to estimate ranking quality before relevance judgments are available. Query performance prediction (QPP) addresses this need, but most existing methods rely on external predi
Shared by @reachsumit.com ↗arxiv.org1mo agoModern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bot
arxiv.org·Hacker News: Front Page·2mo ago·2 min readFast Diversification for Search & Retrieval. Contribute to Pringled/pyversity development by creating an account on GitHub.
github.com·Hacker News: Front Page·9mo ago·4 min read
