Ad Auctions for LLMs via Retrieval Augmented Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912427104272384 |
|---|---|
| author | Hajiaghayi, MohammadTaghi Lahaie, Sébastien Rezaei, Keivan Shin, Suho |
| author_facet | Hajiaghayi, MohammadTaghi Lahaie, Sébastien Rezaei, Keivan Shin, Suho |
| contents | In the field of computational advertising, the integration of ads into the outputs of large language models (LLMs) presents an opportunity to support these services without compromising content integrity. This paper introduces novel auction mechanisms for ad allocation and pricing within the textual outputs of LLMs, leveraging retrieval-augmented generation (RAG). We propose a segment auction where an ad is probabilistically retrieved for each discourse segment (paragraph, section, or entire output) according to its bid and relevance, following the RAG framework, and priced according to competing bids. We show that our auction maximizes logarithmic social welfare, a new notion of welfare that balances allocation efficiency and fairness, and we characterize the associated incentive-compatible pricing rule. These results are extended to multi-ad allocation per segment. An empirical evaluation validates the feasibility and effectiveness of our approach over several ad auction scenarios, and exhibits inherent tradeoffs in metrics as we allow the LLM more flexibility to allocate ads. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09459 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Ad Auctions for LLMs via Retrieval Augmented Generation Hajiaghayi, MohammadTaghi Lahaie, Sébastien Rezaei, Keivan Shin, Suho Computer Science and Game Theory Artificial Intelligence Computation and Language Machine Learning In the field of computational advertising, the integration of ads into the outputs of large language models (LLMs) presents an opportunity to support these services without compromising content integrity. This paper introduces novel auction mechanisms for ad allocation and pricing within the textual outputs of LLMs, leveraging retrieval-augmented generation (RAG). We propose a segment auction where an ad is probabilistically retrieved for each discourse segment (paragraph, section, or entire output) according to its bid and relevance, following the RAG framework, and priced according to competing bids. We show that our auction maximizes logarithmic social welfare, a new notion of welfare that balances allocation efficiency and fairness, and we characterize the associated incentive-compatible pricing rule. These results are extended to multi-ad allocation per segment. An empirical evaluation validates the feasibility and effectiveness of our approach over several ad auction scenarios, and exhibits inherent tradeoffs in metrics as we allow the LLM more flexibility to allocate ads. |
| title | Ad Auctions for LLMs via Retrieval Augmented Generation |
| topic | Computer Science and Game Theory Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2406.09459 |