# A Crowdsourced Study of ChatBot Influence in Value-Driven Decision Making Scenarios

arXiv: https://arxiv.org/abs/2511.15857 · HTML: https://mlsanity.com/paper/2511.15857/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 47 references that are in the map.
- First posted on arXiv 19 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [Why and When LLM-Based Assistants Can Go Wrong: Investigating the Effectiveness of Prompt-Based Interactions for Software Help-Seeking](https://mlsanity.com/paper/2402.08030/) (2024)
- [ChatGPT: More than a Weapon of Mass Deception, Ethical challenges and responses from the Human-Centered Artificial Intelligence (HCAI) perspective](https://mlsanity.com/paper/2304.11215/) (2023)
- [The Levers of Political Persuasion with Conversational AI](https://mlsanity.com/paper/2507.13919/) (2025)
- [Vis Ex Machina: An Analysis of Trust in Human versus Algorithmically Generated Visualization Recommendations](https://mlsanity.com/paper/2101.04251/) (2021)
- [Cyber Security Awareness Campaigns: Why do they fail to change behaviour?](https://mlsanity.com/paper/1901.02672/) (2019)

## Built on by (most cited first, 2 of 2)

- [Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus](https://mlsanity.com/paper/2609.25586/) (2026)
- [The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations](https://mlsanity.com/paper/2610.14124/) (2026)

## Abstract (arXiv)

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.