When Agents Persuade: Propaganda Generation and Mitigation in LLMs

Export BriefConnect with Author
View PDF ↗
PDF Viewer
Open Full PDF

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

Estimated $9K - $13K over 6-10 weeks.

See exactly what it costs to build this -- with 3 comparable funded startups.

7-day free trial. Cancel anytime.

Discover the researchers behind this paper and find similar experts.

7-day free trial. Cancel anytime.

References (36)

[1]
Fine-Tuning a Biased Model for Improving Fairness
2025Huiqiang Chen, Tianqing Zhu et al.
[2]
Are Large Language Models Good at Detecting Propaganda?
2025Julia Jose, Rachel Greenstadt
[3]
Measuring and Benchmarking Large Language Models' Capabilities to Generate Persuasive Language
2024Amalie Brogaard Pauli, Isabelle Augenstein et al.
[4]
Emma Briant on Disinformation Wars
2024E. Briant, E. Martinez et al.
[5]
Limitations of Large Language Models in Propaganda Detection Task
2024Joanna Szwoch, Mateusz Staszkow et al.
[6]
Large Language Models are as persuasive as humans, but how? About the cognitive effort and moral-emotional language of LLM arguments
2024Carlos Carrasco-Farré
[7]
On the conversational persuasiveness of GPT-4
2024Francesco Salvi, Manoel Horta Ribeiro et al.
[8]
ORPO: Monolithic Preference Optimization without Reference Model
2024Jiwoo Hong, Noah Lee et al.
[9]
Balancing Enhancement, Harmlessness, and General Capabilities: Enhancing Conversational LLMs with Direct RLHF
2024Chen Zheng, Ke Sun et al.
[10]
The Dark Side of Language Models: Exploring the Potential of LLMs in Multimedia Disinformation Generation and Dissemination
2024Dipto Barman, Ziyi Guo et al.
[11]
Can GPT-4 Identify Propaganda? Annotation and Detection of Propaganda Spans in News Articles
2024Maram Hasanain, Fatema Ahmed et al.
[12]
How persuasive is AI-generated propaganda?
2024Josh A. Goldstein, Jason Chao et al.
[13]
Ethics and disinformation on the campaign trail: psychiatry, the Goldwater Rule, and the 2024 United States presidential election
2024Alexander J. Smith, Dinesh Bhugra et al.
[14]
The Persuasive Power of Large Language Models
2023Simon Martin Breum, Daniel Vaedele Egdal et al.
[15]
It Takes Two to Negotiate: Modeling Social Exchange in Online Multiplayer Games
2023Kokil Jaidka, Hansin Ahuja et al.
[16]
Adapting Fake News Detection to the Era of Large Language Models
2023Jinyan Su, Claire Cardie et al.
[17]
Large Language Models Can Argue in Convincing Ways About Politics, But Humans Dislike AI Authors: implications for Governance
2023Alexis Palmer, A. Spirling
[18]
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
2023Rafael Rafailov, Archit Sharma et al.
[19]
QLoRA: Efficient Finetuning of Quantized LLMs
2023Tim Dettmers, Artidoro Pagnoni et al.
[20]
Synthetic Lies: Understanding AI-Generated Misinformation and Evaluating Algorithmic and Human Solutions
2023Jiawei Zhou, Yixuan Zhang et al.

Showing 20 of 36 references

Founder's Pitch

"Develop tools to mitigate propaganda generation in LLMs by leveraging optimization techniques."

AI Safety and EthicsScore: 2View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

0/4 signals

0

Quick Build

1/4 signals

2.5

Series A Potential

1/4 signals

2.5

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 3/4/2026

Explore the full citation network and related research.

7-day free trial. Cancel anytime.

Understand the commercial significance and market impact.

7-day free trial. Cancel anytime.

Get detailed profiles of the research team.

7-day free trial. Cancel anytime.

Related Papers

Loading…