Measuring Brand and Source Discovery under Repeated LLM Queries: A Finite-Sample Audit

arXiv:2609.05059 · cs.IR, cs.CL · Submitted 2026-09-04 · Read on arXiv

cs.IR, cs.CL

Submitted: 2026-09-04

Updated: 2026-09-23

Comments: 6 pages, 2 figures, 2 tables, code, per-cell tables and data pointers at github.com/Rankfor/rankfor-open (research/recommendation-saturation)

Code: https://github.com/Rankfor/rankfor-open

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Perplexity — 3× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Provenance — 1× in this paper · explained in 4 episodes

Sources

• Non-Determinism of "Deterministic" LLM Settings
• Prompt Repetition Improves Non-Reasoning LLMs
• Where Does the Noise Come From? A Variance-Components Decomposition of Non-Determinism in LLM Brand Answers
• The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations
• Who Owns the AI Recommendation? A Multi-Industry Empirical Map of Brand Category Ownership Across Large Language Models
• News Source Citing Patterns in AI Search Systems

Related papers

• The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
• SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
• MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
• RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
• Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
• UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG