Prominence-Stratified Failure Modes in Retrieval-Augmented Commercial Recommendation: A 37,000-Run Audit

2026-05-22 · Will Jack, Noah Lehman, Keller Maloney, Sarah Xu arxiv

AI assistants like ChatGPT and Claude are recommendation engines, not search engines: they answer commercial queries by directly nominating brands rather than returning a list of links. Marketing to AI is therefore a broader problem than "show up in search" -- positioning, content, and product fit matter as much as discoverability. We audit ~37,000 production runs across four model configurations and 215 commercially-framed prompts spanning 19 sectors, evaluated against a 533-brand reference catalog stratified into five prominence tiers (L1 category leaders to L5 regional players) sourced from external authority lists. The ladder proxies a brand's awareness footprint within its sector, not revenue or market share. The failure mode differs sharply by tier. L1 brands appear in nearly every relevant retrieval but win only 25-41% of the recommendation slots they reach -- the leverage is differentiation, not visibility. L2 challengers carry the highest conversion rates of any tier (37-52%) but lose to persona-mediated substitution on the Anthropic models. L3 mid-market brands are the inflection level: aggregate coverage drops to 88%, conversion to 34-40%, and persona effects peak. L4 specialists and L5 regional players face catastrophic invisibility -- 48-52% never surface in any of the 37,000 runs. No uniform optimization recipe wins; the right marketing investment depends on where the brand sits on the prominence ladder.

📄 PDF Abstract BibTeX arXiv:2605.27439

Code (0)

등록된 구현이 없습니다.

CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning

2026-04-01 · Xudong Wang, Zilong Wang, Kui Su, Zhaoyan Ming arxiv

Retrieval-Augmented Generation (RAG) frameworks typically process all queries through a one-size-fits-all pipeline, ignoring the heterogeneous cognitive demands of different tasks. This cognitive-blind approach causes tw…

Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation

2026-04-22 · Andrew Klearman, Radu Revutchi, Rohin Garg, Rishav Chakravarti 외 arxiv

Retrieval quality is the primary bottleneck for accuracy and robustness in retrieval-augmented generation (RAG). Current evaluation relies on heuristically constructed query sets, which introduce a hidden intrinsic bias.…

Select-And-Extract: A Lightweight Plugin for Retrieval-Augmented Generation

2026-08-01 · Chenming Tang, Jiawei Han arxiv

Retrieval-augmented generation (RAG) for language model (LM) systems fundamentally has two failure modes: retrieval failure and reading failure. The former fails to recall the right pieces of information from the externa…

Fibres of Failure: Classifying errors in predictive processes

2018-02-09 · Leo Carlsson, Gunnar Carlsson, Mikael Vejdemo-Johansson

We describe Fibres of Failure (FiFa), a method to classify failure modes of predictive processes using the Mapper algorithm from Topological Data Analysis. Our method uses Mapper to build a graph model of input data st…

General Classification Topological Data Analysis

Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit

2026-05-28 · Will Jack, Noah Lehman, Keller Maloney, Sarah Xu arxiv

The same prompt -- "best CRM software" -- reaches AI assistants from buyers in widely different contexts: a solo founder, an enterprise VP, a UK SMB owner. We audit how strongly that contextual variation reshapes which b…