AI RESEARCH
The 99% Success Paradox: When Near-Perfect Retrieval Equals Random Selection
arXiv CS.AI
•
ArXi:2605.18857v1 Announce Type: cross For most of the history of information retrieval (IR), search results were designed for human consumers who could scan, filter, and discard irrelevant information on their own. This shaped retrieval systems to optimize for finding and ranking relevant documents, but not keeping results clean and minimal, as the human was the final filter. However, LLMs have changed that by lacking this filtering ability.