mlsanityData to 7 Oct 2026

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

arXiv 2605.27439 ↗First posted 22 May 2026cs.IR cs.AIcited by 1

On the map: Retrieval-augmented generation → RAG for recommendation

Abstract (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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in RAG for recommendation, one of 15 directions in Retrieval-augmented generation. Builds on 7 of its 17 references that are in the map. First posted on arXiv 22 May 2026.

Builds on

7 of 17 references.

References · 7

  1. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  2. 2023GEO: Generative Engine Optimizationcited by 53
  3. 2023A Survey on Popularity Bias in Recommender Systemscited by 42
  4. 2024Large Language Models as Recommender Systems: A Study of Popularity Biascited by 25
  5. 2025Generative Engine Optimization: How to Dominate AI Searchcited by 16
  6. 2025Revealing Potential Biases in LLM-Based Recommender Systems in the Cold Start Settingcited by 6
  7. 2026Auditing Preferences for Brands and Cultures in LLMscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Auditcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026The User Asks, Platforms Compete: How Agentic Recommendation Markets Take Shape
  2. 2026Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration
  3. 2026Generative AI Advertising as a Problem of Trustworthy Commercial Intervention
  4. 2026Commercial Persuasion in AI-Mediated Conversations
  5. 2026Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baseline
  6. 2026AURA: Agentic Diagnosis and Refinement for Production Recommender Systems at Scale
  7. 2023Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems
  8. 2026Scaling Articulated Rationales for MLLM-based Recommendation