AuthGR: What Authority-Aware Generative Retrieval Changes
An ACL 2026 industry paper connects authority-aware retrieval with stronger ranking judgments and higher click behavior inside a commercial search system.
Tagged collection
Latest articles tagged “information-retrieval”
Open an article for the complete method, evidence, limitations, and a focused reader discussion.
-
-
Top-500 Retrieval Still Missed Useful Evidence
Re:CAP recovered relevant documents missed by flat retrieval, including gaps left by a 1,500-candidate ensemble. That changes how retrieval coverage should be audited.
-
Generative Search Ads Split Relevance, CTR and Revenue
A Meituan paper reports a seven-day test of objective-specific generative ad retrieval, with separate relevance, click and commercial policies.
-
Algebraic Retrieval: 38 Tests Passed, With One Reproduction Limit
We ran the portable Algebraic Retrieval suite and verified its receipt hash. The full 11,429-document Java fixture remains outside this local test.
-
Perplexity Python Search SDK: What Is Open, What Is Compiled and How to Test It
Perplexity’s Python Search SDK offers live web search, fan-out and snippets. This audit separates the open wrapper, compiled core and measurable retrieval output.
-
Google Research Cut Retrieval Fan-Out Time 12× to 20×
Google researchers report that Retrieve-for-Train generated ten retrieval directions 12× to 20× faster in fashion and music benchmarks, while the diffusion model traded some recall for greater diversity.
-
What Perplexity’s CobbleDB Reveals About AI Search Retrieval
Perplexity reports roughly 80% lower read latency after separating passage processing, publishing and hot retrieval. Here is what publishers can and cannot infer.
-
Q2D-Web Shows Why AI Citations Depend on First-Stage Retrieval
A 190-million-document benchmark shows why retrieval recall, unique evidence coverage and downstream citations must be measured separately.
