mlsanityData to 14 Oct 2026

Neutralizing the Narrative: AI-Powered Debiasing of Online News Articles

arXiv 2504.03520 ↗First posted 4 Apr 2025cs.CL cs.CYcited by 4

Not on the map. Why?

Abstract (arXiv)

Bias in news reporting significantly impacts public perception, particularly regarding crime, politics, and societal issues. Traditional bias detection methods, predominantly reliant on human moderation, suffer from subjective interpretations and scalability constraints. Here, we introduce an AI-driven framework leveraging advanced large language models (LLMs), specifically GPT-4o, GPT-4o Mini, Gemini Pro, Gemini Flash, Llama 8B, and Llama 3B, to systematically identify and mitigate biases in news articles. To this end, we collect an extensive dataset consisting of over 30,000 crime-related articles from five politically diverse news sources spanning a decade (2013-2023). Our approach employs a two-stage methodology: (1) bias detection, where each LLM scores and justifies biased content at the paragraph level, validated through human evaluation for ground truth establishment, and (2) iterative debiasing using GPT-4o Mini, verified by both automated reassessment and human reviewers. Empirical results indicate GPT-4o Mini's superior accuracy in bias detection and effectiveness in debiasing. Furthermore, our analysis reveals temporal and geographical variations in media bias correlating with socio-political dynamics and real-world events. This study contributes to scalable computational methodologies for bias mitigation, promoting fairness and accountability in news reporting.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 34 of its 73 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

34 of 73 references.

References · 34

  1. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  2. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  3. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 981
  4. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  5. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 799
  6. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
  7. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  8. 2020Null It Out: Guarding Protected Attributes by Iterative Nullspace Projectioncited by 455
  9. 2019On Measuring Social Biases in Sentence Encoderscited by 398
  10. 2019Measuring Bias in Contextualized Word Representationscited by 276
  11. 2019Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Themcited by 268
  12. 2019Gender Bias in Contextualized Word Embeddingscited by 203
22 more
  1. 2020Towards Debiasing Sentence Representationscited by 171
  2. 2018Learning Gender-Neutral Word Embeddingscited by 169
  3. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  4. 2019Fine-Grained Analysis of Propaganda in News Articlescited by 133
  5. 2023The science of fake newscited by 97
  6. 2019Evaluating the Underlying Gender Bias in Contextualized Word Embeddingscited by 94
  7. 2020Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT modelcited by 87
  8. 2024Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perceptioncited by 56
  9. 2024Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Imagescited by 55
  10. 2023ROBBIE: Robust Bias Evaluation of Large Generative Language Modelscited by 53
  11. 2022POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detectioncited by 51
  12. 2024What's in a Name? Auditing Large Language Models for Race and Gender Biascited by 51
  13. 2019Unsupervised User Stance Detection on Twittercited by 45
  14. 2024Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Modelscited by 33
  15. 2022Dbias: Detecting biases and ensuring Fairness in news articlescited by 28
  16. 2021Dictionary-based Debiasing of Pre-trained Word Embeddingscited by 24
  17. 2022Exploiting Transformer-based Multitask Learning for the Detection of Media Bias in News Articlescited by 11
  18. 2024Quantifying Generative Media Bias with a Corpus of Real-world and Generated News Articlescited by 9
  19. 2025Are generative models fair? A study of racial bias in dermatological image generationcited by 7
  20. 2023Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysiscited by 4
  21. 2024IndiTag: An Online Media Bias Analysis System Using Fine-Grained Bias Indicatorscited by 2
  22. 2024Enhancing Media Literacy: The Effectiveness of (Human) Annotations and Bias Visualizations on Bias Detectioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026Evaluating Decision Models for Text Annotation in Computational Social Sciencecited by 11
  2. 2025Benchmarking the Legal Reasoning of LLMs in Arabic Islamic Inheritance Casescited by 1
  3. 2025Benchmarking the Medical Understanding and Reasoning of Large Language Models in Arabic Healthcare Taskscited by 0
  4. 2026Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectivenesscited by 0