A large-scale audit of AI commercial recommendations reveals tier-specific failure modes: L1 brands reach recommendations but convert at 25-41%, L2 convert highest at 37-52%, L3 is an inflection point, and L4/L5 brands suffer 48-52% complete invisibility.
Generative engine optimization: How to dominate ai search
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
AI Overviews and Gemini retrieve substantially different sources than traditional Google search (Jaccard similarity <0.2), favor Google-owned content, appear for 51.5% of queries especially controversial ones, and are less consistent across repeated or slightly edited queries.
Deep-research agents have a concentrated attack surface because they repeatedly retrieve the same UGC pages, allowing a single poisoned page to affect citations and entity promotion across query clusters in systems like STORM, Co-STORM, and OmniThink.
A measurement study of 602 prompts across ChatGPT, Google AI Overview, and Perplexity finds that citation selection breadth and absorption depth diverge, with high-influence pages being longer, structured, and evidence-rich.
LLMs cite third-party domains for 85.7% of brand attributions, with Wikipedia dominant in most languages, a long-tailed domain distribution, and market-specific shifts such as YouTube and HR sites in Poland.
Gradient-based and instruction-override prompt injections largely fail to survive retrieval and reranking in realistic RAG systems, while only LLM-driven injections remain effective end-to-end, and all attacks are detectable by a lightweight guard.
MaxShapley computes fair document attributions in generative QA by reducing Shapley value calculation to polynomial time via a max-sum utility, matching exact Shapley quality on HotPotQA, MuSiQUE, and MS MARCO while using up to 9x fewer resources.
citing papers explorer
-
Prominence-Stratified Failure Modes in Retrieval-Augmented Commercial Recommendation: A 37,000-Run Audit
A large-scale audit of AI commercial recommendations reveals tier-specific failure modes: L1 brands reach recommendations but convert at 25-41%, L2 convert highest at 37-52%, L3 is an inflection point, and L4/L5 brands suffer 48-52% complete invisibility.
-
How Generative AI Disrupts Search: An Empirical Study of Google Search, Gemini, and AI Overviews
AI Overviews and Gemini retrieve substantially different sources than traditional Google search (Jaccard similarity <0.2), favor Google-owned content, appear for 51.5% of queries especially controversial ones, and are less consistent across repeated or slightly edited queries.
-
Deep-Research Agents Can Be Poisoned via User-Generated Content
Deep-research agents have a concentrated attack surface because they repeatedly retrieve the same UGC pages, allowing a single poisoned page to affect citations and entity promotion across query clusters in systems like STORM, Co-STORM, and OmniThink.
-
From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platforms
A measurement study of 602 prompts across ChatGPT, Google AI Overview, and Perplexity finds that citation selection breadth and absorption depth diverge, with high-influence pages being longer, structured, and evidence-rich.
-
How Large Language Models Source Brand Reputation Across Languages and Markets
LLMs cite third-party domains for 85.7% of brand attributions, with Wikipedia dominant in most languages, a long-tailed domain distribution, and market-specific shifts such as YouTube and HR sites in Poland.
-
Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
Gradient-based and instruction-override prompt injections largely fail to survive retrieval and reranking in realistic RAG systems, while only LLM-driven injections remain effective end-to-end, and all attacks are detectable by a lightweight guard.
-
MaxShapley: Towards Incentive-compatible Generative Search with Fair Context Attribution
MaxShapley computes fair document attributions in generative QA by reducing Shapley value calculation to polynomial time via a max-sum utility, matching exact Shapley quality on HotPotQA, MuSiQUE, and MS MARCO while using up to 9x fewer resources.