Additional Experimental Results

Table of Links

Abstract and 1. Introduction

2 Related Work

3 Method and 3.1 Preliminaries

3.2 Adaptive-RAG: Adaptive Retrieval-Augmented Generation

4 Experimental Setups and 4.1 Datasets

4.2 Models and 4.3 Evaluation Metrics

4.4 Implementation Details

5 Experimental Results and Analyses

6 Conclusion, Limitations, Ethics Statement, Acknowledgements, and References

A Additional Experimental Setups

B Additional Experimental Results

B Additional Experimental Results

Performance vs Time We further provide a comparison of different retrieval-augmented generation approaches with FLAN-T5-XL and FLAN-T5- XXL models in Figure 4 and Figure 5, respectively, in the context of performance and efficiency tradeoffs. Similar to the observation made from the GPT3.5 model in Figure 1, our proposed Adaptive-RAG is significantly more effective as well as efficient.

Table 7: Results on each of a collection of datasets with FLAN-T5-XXL (11B) as the LLM. We emphasize our results in bold.

Table 8: Results on each of a collection of datasets with GPT-3.5 (Turbo) as the LLM. We emphasize our results in bold.

Performance per Dataset In addition to detailing the performance of each dataset with the FLANT5-XL model, as shown in Table 2, we also present the results for each dataset with the FLAN-T5- XXL and GPT-3.5 models in Table 2 and Table 8, respectively. The experimental results show that our Adaptive-RAG consistently balances between efficiency and accuracy. It is worth noting that while the GPT-3.5 model performs effectively in addressing straightforward queries even without document retrieval, it benefits significantly from our Adaptive-RAG in terms of effectiveness when solving complex multi-hop queries.