Meta-prompting Optimized Retrieval-augmented Generation
This addresses performance degradation in retrieval-augmented generation for tasks like multi-hop question answering, though it appears incremental as it refines an existing approach.
The paper tackled the problem of excessive or unfocused retrieved content harming retrieval-augmented generation by proposing a meta-prompting optimization method to refine content before inclusion in prompts, resulting in over 30% improvement on the StrategyQA dataset compared to a baseline system.
Retrieval-augmented generation resorts to content retrieved from external sources in order to leverage the performance of large language models in downstream tasks. The excessive volume of retrieved content, the possible dispersion of its parts, or their out of focus range may happen nevertheless to eventually have a detrimental rather than an incremental effect. To mitigate this issue and improve retrieval-augmented generation, we propose a method to refine the retrieved content before it is included in the prompt by resorting to meta-prompting optimization. Put to empirical test with the demanding multi-hop question answering task from the StrategyQA dataset, the evaluation results indicate that this method outperforms a similar retrieval-augmented system but without this method by over 30%.