Saved in:
Bibliographic Details
Main Author: Cisneros-Velarde, Pedro
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.06260
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911425999405056
author Cisneros-Velarde, Pedro
author_facet Cisneros-Velarde, Pedro
contents Polemic questions need more than one viewpoint to express a balanced answer. Large Language Models (LLMs) can provide a balanced answer, but also take a single aligned viewpoint or refuse to answer. In this paper, we study if such initial responses can be steered to a specific viewpoint in a simple and intuitive way: by only providing one-sided arguments supporting the viewpoint. Our systematic study has three dimensions: (i) which stance is induced in the LLM response, (ii) how the polemic question is formulated, (iii) how the arguments are shown. We construct a small dataset and remarkably find that opinion steering occurs across (i)-(iii) for diverse models, number of arguments, and topics. Switching to other arguments consistently decreases opinion steering.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06260
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Can One-sided Arguments Lead to Response Change in Large Language Models?
Cisneros-Velarde, Pedro
Computation and Language
Artificial Intelligence
Polemic questions need more than one viewpoint to express a balanced answer. Large Language Models (LLMs) can provide a balanced answer, but also take a single aligned viewpoint or refuse to answer. In this paper, we study if such initial responses can be steered to a specific viewpoint in a simple and intuitive way: by only providing one-sided arguments supporting the viewpoint. Our systematic study has three dimensions: (i) which stance is induced in the LLM response, (ii) how the polemic question is formulated, (iii) how the arguments are shown. We construct a small dataset and remarkably find that opinion steering occurs across (i)-(iii) for diverse models, number of arguments, and topics. Switching to other arguments consistently decreases opinion steering.
title Can One-sided Arguments Lead to Response Change in Large Language Models?
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2602.06260