# Ad Insertion in LLM-Generated Responses

arXiv: https://arxiv.org/abs/2601.19435 · HTML: https://mlsanity.com/paper/2601.19435/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 60 references that are in the map.
- First posted on arXiv 27 Jan 2026.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [Benchmarking Foundation Models with Language-Model-as-an-Examiner](https://mlsanity.com/paper/2306.04181/) (2023)
- [CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation](https://mlsanity.com/paper/2311.18702/) (2023)
- [PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendations](https://mlsanity.com/paper/2510.07784/) (2025)
- [The Challenge of Understanding What Users Want: Inconsistent Preferences and Engagement Optimization](https://mlsanity.com/paper/2202.11776/) (2022)
- [Truthful Aggregation of LLMs with an Application to Online Advertising](https://mlsanity.com/paper/2405.05905/) (2024)
- [Auctions with LLM Summaries](https://mlsanity.com/paper/2404.08126/) (2024)
- [Benchmarking LLMs' Judgments with No Gold Standard](https://mlsanity.com/paper/2411.07127/) (2024)
- [Ad Auctions for LLMs via Retrieval Augmented Generation](https://mlsanity.com/paper/2406.09459/) (2024)
- [Online Advertisements with LLMs: Opportunities and Challenges](https://mlsanity.com/paper/2311.07601/) (2023)
- [Eliciting Informative Text Evaluations with Large Language Models](https://mlsanity.com/paper/2405.15077/) (2024)
- [Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising](https://mlsanity.com/paper/1607.01869/) (2016)
- [LLM-Auction: Generative Auction towards LLM-Native Advertising](https://mlsanity.com/paper/2512.10551/) (2025)
- [Sponsored Question Answering](https://mlsanity.com/paper/2407.04471/) (2024)
- [Data-Driven Mechanism Design: Jointly Eliciting Preferences and Information](https://mlsanity.com/paper/2412.16132/) (2024)
- [Ads in Conversations](https://mlsanity.com/paper/2403.11022/) (2024)
- [Recommendation and Temptation](https://mlsanity.com/paper/2412.10595/) (2024)

## Built on by (most cited first, 8 of 8)

- [LLM Advertisement based on Neuron Auctions](https://mlsanity.com/paper/2605.08326/) (2026)
- [NaiAD: Initiate Data-Driven Research for LLM Advertising](https://mlsanity.com/paper/2605.09918/) (2026)
- [LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots](https://mlsanity.com/paper/2605.16474/) (2026)
- [PILA: Plug-and-Play Insertion for LLM-native Advertising](https://mlsanity.com/paper/2607.25590/) (2026)
- [Generative AI Advertising as a Problem of Trustworthy Commercial Intervention](https://mlsanity.com/paper/2605.18673/) (2026)
- [Evaluating and Pricing Advertisements in AI-Generated Responses](https://mlsanity.com/paper/2607.27686/) (2026)
- [Token-Level Advertising](https://mlsanity.com/paper/2608.27382/) (2026)
- [LLMAdBench: A Human Preference Benchmark for Advertising in LLM Responses](https://mlsanity.com/paper/2609.32533/) (2026)

## Abstract (arXiv)

Sustainable monetization of large language models (LLMs) remains a critical open challenge. Traditional search advertising, which relies on static keywords, fails to capture the fleeting, context-dependent user intent---the specific information, goods, or services a user seeks---embedded in conversational flows. Beyond the standard goal of social welfare maximization effective LLM advertising requires contextual coherence (aligning ads semantically with transient user intent), computational efficiency (avoiding user-facing latency), and adherence to ethical and regulatory standards, including privacy preservation and explicit ad disclosure. Although recent solutions have explored bidding at the token and query levels, neither category holistically satisfies these constraints. We propose a framework that resolves these tensions through two decoupling strategies. First, we decouple ad insertion from response generation to facilitate pre-screening and explicit disclosure. Second, we decouple bidding from specific user queries by using ``genres'' (high-level semantic clusters) as a proxy. This allows advertisers to bid on stable categories rather than sensitive real-time responses, reducing computational burden and privacy risks. Applying the VCG auction mechanism to this genre-based framework provides approximate guarantees for dominant-strategy incentive compatibility (DSIC), individual rationality (IR), and social welfare. In synthetic experiments with 105 advertisers and 100 candidate slots, VCG clears in approximately 1.25 seconds on a consumer-grade laptop. Finally, we introduce an ``LLM-as-a-Judge'' metric for estimating contextual coherence. Its predictions correlate with mean human ratings at Spearman's ρ≈ 0.66 and have a higher correlation with the leave-one-out group mean than 29 of 36 individual raters (80.6%).