Researchers have introduced a new evaluation metric called Rank-Deviation Quality (RDQ) designed for retrieval and ranking systems. RDQ is adaptable to queries with varying numbers of correct answers, from a single result to multiple valid options. It scores candidate rankings by considering the position of retrieved reference items and a penalty for rank deviation, with parameters to control tolerance for misordering. RDQ operates on ordinal rankings, making it suitable for annotators using pairwise or listwise judgments, and it accounts for both the items returned and their order. AI
IMPACT This new metric could improve the evaluation of AI-powered search and recommendation systems by better handling queries with multiple valid results.
RANK_REASON The cluster contains a research paper introducing a new metric for information retrieval systems. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →