DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models2024
- Exploring Hint Generation Approaches for Open-Domain Question Answering2024
- Exploring the state of the art in legal QA systemsJournal of Big Data, 2023
- Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents2023
- Precise Zero-Shot Dense Retrieval without Relevance Labels2023
- Improving Passage Retrieval with Zero-Shot Question Generation2022
- Natural Questions: A Benchmark for Question Answering ResearchTransactions of the Association for Computational Linguistics, 2019
- Investigating the transferring capability of capsule networks for text classificationNeural Networks, 2019
- Representation Learning for Question Classification via Topic Sparse Autoencoder and Entity Embedding2018
- Feature extraction based on information gain and sequential pattern for English question classificationIET Software, 2018