# LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots

arXiv: https://arxiv.org/abs/2605.16474 · HTML: https://mlsanity.com/paper/2605.16474/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 15 May 2026.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Is ChatGPT a Good Recommender? A Preliminary Study](https://mlsanity.com/paper/2304.10149/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [Uncovering ChatGPT's Capabilities in Recommender Systems](https://mlsanity.com/paper/2305.02182/) (2023)
- [Large Language Models for Generative Recommendation: A Survey and Visionary Discussions](https://mlsanity.com/paper/2309.01157/) (2023)
- [Limitations of Language Models in Arithmetic and Symbolic Induction](https://mlsanity.com/paper/2208.05051/) (2022)
- [Neural Auction: End-to-End Learning of Auction Mechanisms for E-Commerce Advertising](https://mlsanity.com/paper/2106.03593/) (2021)
- [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)
- [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)
- [Optimizing Multiple Performance Metrics with Deep GSP Auctions for E-commerce Advertising](https://mlsanity.com/paper/2012.02930/) (2020)
- [LLM-Auction: Generative Auction towards LLM-Native Advertising](https://mlsanity.com/paper/2512.10551/) (2025)
- [Ad Insertion in LLM-Generated Responses](https://mlsanity.com/paper/2601.19435/) (2026)
- [Sponsored Question Answering](https://mlsanity.com/paper/2407.04471/) (2024)
- [Deep Automated Mechanism Design for Integrating Ad Auction and Allocation in Feed](https://mlsanity.com/paper/2401.01656/) (2024)
- [LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System](https://mlsanity.com/paper/2411.13789/) (2024)
- [Against Opacity: Explainable AI and Large Language Models for Effective Digital Advertising](https://mlsanity.com/paper/2504.20064/) (2025)

## Built on by (most cited first, 2 of 2)

- [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)

The integration of advertising auction mechanisms into large language model (LLM)-based chatbots presents a significant opportunity for commercialization, yet poses unique challenges in balancing relevance, efficiency, and user experience. Recently, Feizi et al.~citepfeizi2023online and Hajiaghayi et al.~citephajiaghayi2024ad outlined a retrieve-then-generate paradigm that decouples retrieval and generation, offering lightweight ad insertion and payment determination. However, current retrieval relies solely on text embedding similarity, which may lead to commercial misinterpretation and issues such as repetitive insertions. In this paper, we propose LERA, a two-stage retrieve-then-generate auction framework tailored for LLM chatbots. In the first stage, embedding-based coarse filtering pre-selects a small set of candidate advertisers. In the second stage, the LLM itself is queried with a carefully designed prompt to produce logits over candidates, which serve as refined organic relevance scores. These scores are combined with bids, and a critical-value payment rule accounts for both the coarse-filtering and fine-ranking thresholds, ensuring truthfulness for utility-maximizing advertisers. The framework naturally extends to multiple ad insertions within dynamic dialogue flows and long responses. Experiments on a synthetic advertiser-query benchmark show that LERA substantially improves ad selection accuracy and insertion diversity while incurring only controllable latency overhead.