Saved in:
| Main Author: | |
|---|---|
| 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 |