On the Merits of LLM-Based Corpus Enrichment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913881563070464 |
|---|---|
| author | Zur, Gal Mordo, Tommy Tennenholtz, Moshe Kurland, Oren |
| author_facet | Zur, Gal Mordo, Tommy Tennenholtz, Moshe Kurland, Oren |
| contents | Generative AI (genAI) technologies -- specifically, large language models (LLMs) -- and search have evolving relations. We argue for a novel perspective: using genAI to enrich a document corpus so as to improve query-based retrieval effectiveness. The enrichment is based on modifying existing documents or generating new ones. As an empirical proof of concept, we use LLMs to generate documents relevant to a topic which are more retrievable than existing ones. In addition, we demonstrate the potential merits of using corpus enrichment for retrieval augmented generation (RAG) and answer attribution in question answering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06015 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the Merits of LLM-Based Corpus Enrichment Zur, Gal Mordo, Tommy Tennenholtz, Moshe Kurland, Oren Information Retrieval Generative AI (genAI) technologies -- specifically, large language models (LLMs) -- and search have evolving relations. We argue for a novel perspective: using genAI to enrich a document corpus so as to improve query-based retrieval effectiveness. The enrichment is based on modifying existing documents or generating new ones. As an empirical proof of concept, we use LLMs to generate documents relevant to a topic which are more retrievable than existing ones. In addition, we demonstrate the potential merits of using corpus enrichment for retrieval augmented generation (RAG) and answer attribution in question answering. |
| title | On the Merits of LLM-Based Corpus Enrichment |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2506.06015 |