Backend
NONSENSE: Non-Semantic Strings Expose Semanticity Gaps in Dense Retrieval
arXiv cs.IR0 views
arXiv:2611.22353v1 Announce Type: new Abstract: Dense retrieval is central to modern search, question answering, and retrieval-augmented generation, where high similarity is often treated as evidence of semantic relevance. We examine how far this assumption can be stressed. NONSENSE is a black-box sparse-edit probe that constructs visibly non-semantic strings while forbidding query-term copying, optimizing only the dense similarity between a query and the string. Across five BEIR-style datasets and three popular single-vector retrievers, these strings frequently outscore the retriever's own best judged query-relevant passage (QRP), and often rank first in the full corpus. The result indicates a semanticity gap in the evaluated dense retrievers: nearest-neighbor status can be separated from passage-like meaning. These findings highlight the importance of evaluating dense retrievers not only by whether they retrieve relevant documents, but also by how reliably their similarity scores reflect semantic evidence.
Source:https://arxiv.org/abs/2611.22353PreviousTeaching Language Models to Narrow Boolean Patent Searches from Search FeedbackNextDeal With It: On Better Schedules for Listwise Reranking
Related posts
Our Guard Checked That We Still Talked About the Fix, Not That We Still Did It
0dev.to

How to Build an Invoice App with Next.js and Firebase Using Claude (With Prompts Included)
0dev.to
One calendar URL, five subscribe links, and the Outlook one Microsoft has never documented
0dev.to
The Hidden Engineering Challenge Behind Smart Construction Sites
0dev.to
WooCommerce Orders Stuck on Pending Payment: How to Fix
0dev.to
WordPress Staging Site: How to Test Changes Safely
0dev.to