More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Vu, Duc Anh, Nguyen, Thong, Nguyen, Cong-Duy, Nguyen, Viet Anh, Luu, Anh Tuan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917102478163968
author Vu, Duc Anh
Nguyen, Thong
Nguyen, Cong-Duy
Nguyen, Viet Anh
Luu, Anh Tuan
author_facet Vu, Duc Anh
Nguyen, Thong
Nguyen, Cong-Duy
Nguyen, Viet Anh
Luu, Anh Tuan
contents With the advancement of large language models (LLMs), their performance on multiple-choice question (MCQ) tasks has improved significantly. However, existing approaches face key limitations: answer choices are typically presented to LLMs without contextual grounding or explanation. This absence of context can lead to incomplete exploration of all possible answers, ultimately degrading the models' reasoning capabilities. To address these challenges, we introduce BiasPrompting, a novel inference framework that guides LLMs to generate and critically evaluate reasoning across all plausible answer options before reaching a final prediction. It consists of two components: first, a reasoning generation stage, where the model is prompted to produce supportive reasonings for each answer option, and then, a reasoning-guided agreement stage, where the generated reasonings are synthesized to select the most plausible answer. Through comprehensive evaluations, BiasPrompting demonstrates significant improvements in five widely used multiple-choice question answering benchmarks. Our experiments showcase that BiasPrompting enhances the reasoning capabilities of LLMs and provides a strong foundation for tackling complex and challenging questions, particularly in settings where existing methods underperform.
format Preprint
id arxiv_https___arxiv_org_abs_2511_20086
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering
Vu, Duc Anh
Nguyen, Thong
Nguyen, Cong-Duy
Nguyen, Viet Anh
Luu, Anh Tuan
Computation and Language
With the advancement of large language models (LLMs), their performance on multiple-choice question (MCQ) tasks has improved significantly. However, existing approaches face key limitations: answer choices are typically presented to LLMs without contextual grounding or explanation. This absence of context can lead to incomplete exploration of all possible answers, ultimately degrading the models' reasoning capabilities. To address these challenges, we introduce BiasPrompting, a novel inference framework that guides LLMs to generate and critically evaluate reasoning across all plausible answer options before reaching a final prediction. It consists of two components: first, a reasoning generation stage, where the model is prompted to produce supportive reasonings for each answer option, and then, a reasoning-guided agreement stage, where the generated reasonings are synthesized to select the most plausible answer. Through comprehensive evaluations, BiasPrompting demonstrates significant improvements in five widely used multiple-choice question answering benchmarks. Our experiments showcase that BiasPrompting enhances the reasoning capabilities of LLMs and provides a strong foundation for tackling complex and challenging questions, particularly in settings where existing methods underperform.
title More Bias, Less Bias: BiasPrompting for Enhanced Multiple-Choice Question Answering
topic Computation and Language
url https://arxiv.org/abs/2511.20086