DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification
This addresses the issue of static prompts in retrieval systems for QA applications, but it appears incremental as it builds on existing frameworks.
The paper tackles the problem of limited adaptability in passage retrieval for open-domain question-answering by introducing DynRank, a framework that uses dynamic zero-shot prompting based on question classification, and reports results from experiments on multiple QA benchmark datasets.
This paper presents DynRank, a novel framework for enhancing passage retrieval in open-domain question-answering systems through dynamic zero-shot question classification. Traditional approaches rely on static prompts and pre-defined templates, which may limit model adaptability across different questions and contexts. In contrast, DynRank introduces a dynamic prompting mechanism, leveraging a pre-trained question classification model that categorizes questions into fine-grained types. Based on these classifications, contextually relevant prompts are generated, enabling more effective passage retrieval. We integrate DynRank into existing retrieval frameworks and conduct extensive experiments on multiple QA benchmark datasets.