Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.06276 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913784382095360 |
|---|---|
| author | Catapang, Jasper Kyle |
| author_facet | Catapang, Jasper Kyle |
| contents | Yes, repurposing multiple-choice question-answering (MCQA) models for document reranking is both feasible and valuable. This preliminary work is founded on mathematical parallels between MCQA decision-making and cross-encoder semantic relevance assessments, leading to the development of R*, a proof-of-concept model that harmonizes these approaches. Designed to assess document relevance with depth and precision, R* showcases how MCQA's principles can improve reranking in information retrieval (IR) and retrieval-augmented generation (RAG) systems -- ultimately enhancing search and dialogue in AI-powered systems. Through experimental validation, R* proves to improve retrieval accuracy and contribute to the field's advancement by demonstrating a practical prototype of MCQA for reranking by keeping it lightweight. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06276 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Can we repurpose multiple-choice question-answering models to rerank retrieved documents? Catapang, Jasper Kyle Information Retrieval Yes, repurposing multiple-choice question-answering (MCQA) models for document reranking is both feasible and valuable. This preliminary work is founded on mathematical parallels between MCQA decision-making and cross-encoder semantic relevance assessments, leading to the development of R*, a proof-of-concept model that harmonizes these approaches. Designed to assess document relevance with depth and precision, R* showcases how MCQA's principles can improve reranking in information retrieval (IR) and retrieval-augmented generation (RAG) systems -- ultimately enhancing search and dialogue in AI-powered systems. Through experimental validation, R* proves to improve retrieval accuracy and contribute to the field's advancement by demonstrating a practical prototype of MCQA for reranking by keeping it lightweight. |
| title | Can we repurpose multiple-choice question-answering models to rerank retrieved documents? |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2504.06276 |