LLM Advertisement based on Neuron Auctions
Peiran Yun, Wenxin Xu, Jiayuan Liu, Yihang Zhang, Liang Zeng, Lingkai Kong, Tonghan Wang

TL;DR
This paper introduces Neuron Auctions, a novel mechanism for embedding advertisements in LLMs by auctioning internal neurons, balancing revenue, user experience, and semantic coherence.
Contribution
It proposes a parametric auction framework based on interpretability of LLM neurons, enabling independent control and strategy-proof advertising integration.
Findings
Neuron Auctions maintain discourse quality while optimizing revenue.
Brand-specific neurons activate in orthogonal subspaces, enabling auction design.
The framework dynamically prices interventions to prevent overly aggressive advertising.
Abstract
As Large Language Models (LLMs) transition into conversational agents, generative advertising emerges as a crucial monetization strategy. However, embedding advertisements within unstructured LLM outputs introduces a critical trilemma: balancing advertiser payoffs, platform revenue, and user experience. Existing methods, such as prompt injection or rigid position slots, disrupt semantic coherence and lack a parametric framework for independent control, rendering rigorous mechanism design intractable. To bridge this gap, we introduce Neuron Auctions, a novel paradigm that shifts the auction object from the surface text space to the LLM's internal representations. Leveraging mechanistic interpretability, we identify brand-specific feed-forward network (FFN) neurons and demonstrate that competing brands activate within approximately orthogonal subspaces. This near-perfect independence…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
