DynRank: Improving Passage Retrieval with Dynamic Zero-Shot Prompting Based on Question Classification
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 19 of its 41 references that are in the map. First posted on arXiv 30 Nov 2024.
Builds on
19 of 41 references.
References · 19
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
- 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
- 2023Large Language Modelscited by 774
- 2019Passage Re-ranking with BERTcited by 629
- 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
- 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 356
- 2022SGPT: GPT Sentence Embeddings for Semantic Searchcited by 204
- 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
7 more
- 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 151
- 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
- 2015A C-LSTM Neural Network for Text Classificationcited by 54
- 2024ArabicaQA: A Comprehensive Dataset for Arabic Question Answeringcited by 20
- 2019RankQA: Neural Question Answering with Answer Re-Rankingcited by 15
- 2024Exploring Hint Generation Approaches in Open-Domain Question Answeringcited by 7
- 2019Investigating the Successes and Failures of BERT for Passage Re-Rankingcited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.