From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines

ArXi:2604.13468v1 Announce Type: cross 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.