Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.15857 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908665892569088 |
|---|---|
| author | Wise, Anthony Zhou, Xinyi Reimann, Martin Dey, Anind Battle, Leilani |
| author_facet | Wise, Anthony Zhou, Xinyi Reimann, Martin Dey, Anind Battle, Leilani |
| contents | Similar to social media bots that shape public opinion, healthcare and financial decisions, LLM-based ChatBots like ChatGPT can persuade users to alter their behavior. Unlike prior work that persuades via overt-partisan bias or misinformation, we test whether framing alone suffices. We conducted a crowdsourced study, where 336 participants interacted with a neutral or one of two value-framed ChatBots while deciding to alter US defense spending. In this single policy domain with controlled content, participants exposed to value-framed ChatBots significantly changed their budget choices relative to the neutral control. When the frame misaligned with their values, some participants reinforced their original preference, revealing a potentially replicable backfire effect, originally considered rare in the literature. These findings suggest that value-framing alone lowers the barrier for manipulative uses of LLMs, revealing risks distinct from overt bias or misinformation, and clarifying risks to countering misinformation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_15857 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Crowdsourced Study of ChatBot Influence in Value-Driven Decision Making Scenarios Wise, Anthony Zhou, Xinyi Reimann, Martin Dey, Anind Battle, Leilani Human-Computer Interaction Artificial Intelligence Similar to social media bots that shape public opinion, healthcare and financial decisions, LLM-based ChatBots like ChatGPT can persuade users to alter their behavior. Unlike prior work that persuades via overt-partisan bias or misinformation, we test whether framing alone suffices. We conducted a crowdsourced study, where 336 participants interacted with a neutral or one of two value-framed ChatBots while deciding to alter US defense spending. In this single policy domain with controlled content, participants exposed to value-framed ChatBots significantly changed their budget choices relative to the neutral control. When the frame misaligned with their values, some participants reinforced their original preference, revealing a potentially replicable backfire effect, originally considered rare in the literature. These findings suggest that value-framing alone lowers the barrier for manipulative uses of LLMs, revealing risks distinct from overt bias or misinformation, and clarifying risks to countering misinformation. |
| title | A Crowdsourced Study of ChatBot Influence in Value-Driven Decision Making Scenarios |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2511.15857 |