Saved in:
Bibliographic Details
Main Authors: Abdallah, Abdelrahman, Mozafari, Jamshid, Piryani, Bhawna, Abdelgwad, Mohammed M., Jatowt, Adam
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.00600
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909410531475456
author Abdallah, Abdelrahman
Mozafari, Jamshid
Piryani, Bhawna
Abdelgwad, Mohammed M.
Jatowt, Adam
author_facet Abdallah, Abdelrahman
Mozafari, Jamshid
Piryani, Bhawna
Abdelgwad, Mohammed M.
Jatowt, Adam
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_00600
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification
Abdallah, Abdelrahman
Mozafari, Jamshid
Piryani, Bhawna
Abdelgwad, Mohammed M.
Jatowt, Adam
Computation and Language
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.
title DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification
topic Computation and Language
url https://arxiv.org/abs/2412.00600