arXiv AI
Ad Insertion in LLM-Generated Responses
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 16
Attribute Inference from Interactive Targeted Ads
arXiv:2606. 15209v1 Announce Type: new Abstract: Targeted advertising systems can pair audiences selected by advertisers with ad units that expose visible user actions.
arXiv AI
Aug 17
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
arXiv:2604. 08525v2 Announce Type: replace Abstract: Large language models (LLMs) are trained to align with user preferences through methods like reinforcement learning.
arXiv Machine Learning
Aug 4
LLM-OSDA: An Optimal-Stopping Dynamic Auction for Native Advertising in Multi-Turn LLM Conversations
arXiv:2608. 00123v1 Announce Type: cross Abstract: LLM-native advertising embeds sponsored content directly into model-generated responses, shifting the unit of sale from a fixed slot to a moment within an evolving conversation.
arXiv AI
Jul 24
Benchmarking the Personalization Capabilities of Large Language Models
arXiv:2607. 20471v1 Announce Type: new Abstract: Personalization, the act of varying a message to induce action from a specific receiver while keeping sender, channel, and time fixed, has a long tradition in psychology and marketing as a two-party problem in which sender and receiver have independent objectives.
arXiv Machine Learning
2d ago
Token-Level Advertising
The paper introduces the Latent Advertiser Mixture Auction (LAMA), a token‑level advertising framework that integrates advertiser influence directly into the text generation process. Advertisers provide local continuation values that shape next‑token policies, and the platform decodes these through a latent mixture while updating an allocation posterior. LAMA is shown to satisfy Markov DSIC and IR, achieve near‑optimal KL‑regularized welfare, and, in proof‑of‑concept experiments on commercial‑search queries, improve platform welfare and revenue without compromising user‑facing response quality.
Hugging Face Trending Papers
Jun 22
Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models
Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks, but existing studies mainly focus on whether specific samples or sample-based data units are used for training.