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

arXiv: https://arxiv.org/abs/2605.27439 · HTML: https://mlsanity.com/paper/2605.27439/

## Key facts

- Cited by 1 papers in the map (data through 14 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.

## Placed in

- Retrieval-augmented generation / [RAG for recommendation](https://mlsanity.com/rag/rag-for-recommendation/)

## Builds on (most cited first, 7 of 7)

- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [GEO: Generative Engine Optimization](https://mlsanity.com/paper/2311.09735/) (2023)
- [A Survey on Popularity Bias in Recommender Systems](https://mlsanity.com/paper/2308.01118/) (2023)
- [Large Language Models as Recommender Systems: A Study of Popularity Bias](https://mlsanity.com/paper/2406.01285/) (2024)
- [Generative Engine Optimization: How to Dominate AI Search](https://mlsanity.com/paper/2509.08919/) (2025)
- [Revealing Potential Biases in LLM-Based Recommender Systems in the Cold Start Setting](https://mlsanity.com/paper/2508.20401/) (2025)
- [Auditing Preferences for Brands and Cultures in LLMs](https://mlsanity.com/paper/2603.18300/) (2026)

## Built on by (most cited first, 1 of 1)

- [Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider Audit](https://mlsanity.com/paper/2605.30207/) (2026)

## 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.