Biased by Design: Leveraging AI Biases to Enhance Critical Thinking of News Readers
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
This paper explores the design of a propaganda detection tool using Large Language Models (LLMs). Acknowledging the inherent biases in AI models, especially in political contexts, we investigate how these biases might be leveraged to enhance critical thinking in news consumption. Countering the typical view of AI biases as detrimental, our research proposes strategies of user choice and personalization in response to a user's political stance, applying psychological concepts of confirmation bias and cognitive dissonance. We present findings from a qualitative user study, offering insights and design recommendations (bias awareness, personalization and choice, and gradual introduction of diverse perspectives) for AI tools in propaganda detection.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 21 of its 58 references that are in the map. First posted on arXiv 20 Apr 2025.
Builds on
21 of 58 references.
Closest ancestors · 1
Same direction, newest first
Other references · 20
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2023GPT-4 Technical Reportcited by 18,132
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
- 2023Bias and Fairness in Large Language Models: A Surveycited by 626
- 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 582
- 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 376
- 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
- 2018Gender Bias in Neural Natural Language Processingcited by 210
8 more
- 2020A Survey on Computational Propaganda Detectioncited by 69
- 2019Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Functioncited by 57
- 2020Prta: A System to Support the Analysis of Propaganda Techniques in the Newscited by 23
- 2021Detecting Fake News Using Machine Learning : A Systematic Literature Reviewcited by 19
- 2024Think Fast, Think Slow, Think Critical: Designing an Automated Propaganda Detection Toolcited by 9
- 2024Polarization of Autonomous Generative AI Agents Under Echo Chamberscited by 7
- 2022Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewritecited by 5
- 2025Effective Yet Ephemeral Propaganda Defense: There Needs to Be More than One-Shot Inoculation to Enhance Critical Thinkingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Measuring Political Preferences in AI Systems: An Integrative Approach
- 2026Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language Models
- 2026Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups
- 2025Are LLMs (Really) Ideological? An IRT-based Analysis and Alignment Tool for Perceived Socio-Economic Bias in LLMs
- 2025Shots and Boosters: Exploring the Use of Combined Prebunking Interventions to Raise Critical Thinking and Create Long-Term Protection Against Misinformation ↗
- 2025Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data
- 2026NewsLens: A Multi-Agent Framework for Adversarial News Bias Navigation
- 2024Deceptive AI systems that give explanations are more convincing than honest AI systems and can amplify belief in misinformation