Papers by Seonho An
PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for decision making require complex data analysis. |
| Approach: | They propose a method that generates the plan for decision making as the first step and retrieves the queries for data analysis as the second step. |
| Outcome: | The proposed method outperforms the state-of-the-art iterative plan-then-retrieval augmented generation method by 15.8% and 7.4% respectively. |