RAGONITE: Iterative Retrieval on Induced Databases and Verbalized RDF for Conversational QA over KGs with RAG
| Autor: | Roy, Rishiraj Saha, Hinze, Chris, Schlotthauer, Joel, Naderi, Farzad, Hangya, Viktor, Foltyn, Andreas, Hahn, Luzian, Kuech, Fabian |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Conversational question answering (ConvQA) is a convenient means of searching over RDF knowledge graphs (KGs), where a prevalent approach is to translate natural language questions to SPARQL queries. However, SPARQL has certain shortcomings: (i) it is brittle for complex intents and conversational questions, and (ii) it is not suitable for more abstract needs. Instead, we propose a novel two-pronged system where we fuse: (i) SQL-query results over a database automatically derived from the KG, and (ii) text-search results over verbalizations of KG facts. Our pipeline supports iterative retrieval: when the results of any branch are found to be unsatisfactory, the system can automatically opt for further rounds. We put everything together in a retrieval augmented generation (RAG) setup, where an LLM generates a coherent response from accumulated search results. We demonstrate the superiority of our proposed system over several baselines on a knowledge graph of BMW automobiles. Comment: Accepted at BTW 2025, 10 pages |
| Databáze: | arXiv |
| Externí odkaz: |
|