# Can we repurpose multiple-choice question-answering models to rerank retrieved documents?

Source: [Can we repurpose multiple-choice question-answering models to rerank retrieved documents?](<https://www.sota2.com/research/paper/68fa77de1e209131cea75add>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:27:29.052Z

Authors: Jasper Kyle Catapang

Published: 2025-03-06T17:53:24.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2504.06276>)

[PDF](<https://arxiv.org/pdf/2504.06276.pdf>)