From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914488286969856 |
|---|---|
| author | Lee, Sunkyung Back, Jihye Jeon, Donghyeon Kwon, Soonhwan Kim, Moonkwon Kang, Inho Lee, Jongwuk |
| author_facet | Lee, Sunkyung Back, Jihye Jeon, Donghyeon Kwon, Soonhwan Kim, Moonkwon Kang, Inho Lee, Jongwuk |
| contents | Generative information retrieval (GenIR) formulates the retrieval process as a text-to-text generation task, leveraging the vast knowledge of large language models. However, existing works primarily optimize for relevance while often overlooking document trustworthiness. This is critical in high-stakes domains like healthcare and finance, where relying solely on semantic relevance risks retrieving unreliable information. To address this, we propose an Authority-aware Generative Retriever (AuthGR), the first framework that incorporates authority into GenIR. AuthGR consists of three key components: (i) Multimodal Authority Scoring, which employs a vision-language model to quantify authority from textual and visual cues; (ii) a Three-stage Training Pipeline to progressively instill authority awareness into the retriever; and (iii) a Hybrid Ensemble Pipeline for robust deployment. Offline evaluations demonstrate that AuthGR successfully enhances both authority and accuracy, with our 3B model matching a 14B baseline. Crucially, large-scale online A/B tests and human evaluations conducted on the commercial web search platform confirm significant improvements in real-world user engagement and reliability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13468 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines Lee, Sunkyung Back, Jihye Jeon, Donghyeon Kwon, Soonhwan Kim, Moonkwon Kang, Inho Lee, Jongwuk Information Retrieval Computation and Language Generative information retrieval (GenIR) formulates the retrieval process as a text-to-text generation task, leveraging the vast knowledge of large language models. However, existing works primarily optimize for relevance while often overlooking document trustworthiness. This is critical in high-stakes domains like healthcare and finance, where relying solely on semantic relevance risks retrieving unreliable information. To address this, we propose an Authority-aware Generative Retriever (AuthGR), the first framework that incorporates authority into GenIR. AuthGR consists of three key components: (i) Multimodal Authority Scoring, which employs a vision-language model to quantify authority from textual and visual cues; (ii) a Three-stage Training Pipeline to progressively instill authority awareness into the retriever; and (iii) a Hybrid Ensemble Pipeline for robust deployment. Offline evaluations demonstrate that AuthGR successfully enhances both authority and accuracy, with our 3B model matching a 14B baseline. Crucially, large-scale online A/B tests and human evaluations conducted on the commercial web search platform confirm significant improvements in real-world user engagement and reliability. |
| title | From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2604.13468 |