Image de couverture de livre

Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Neumann, Anna, Kirsten, Elisabeth, Zafar, Muhammad Bilal, Singh, Jatinder
Format:	Preprint
Publié:	2025
Sujets:	Computers and Society Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Impact of Inference Acceleration on Bias of LLMs
par: Kirsten, Elisabeth, et autres
Publié: (2024)

Born With a Silver Spoon? Investigating Socioeconomic Bias in Large Language Models
par: Singh, Smriti, et autres
Publié: (2024)

Cross-Language Bias Examination in Large Language Models
par: Liang, Yuxuan, et autres
Publié: (2025)

Ask LLMs Directly, "What shapes your bias?": Measuring Social Bias in Large Language Models
par: Shin, Jisu, et autres
Publié: (2024)

EtiCor++: Towards Understanding Etiquettical Bias in LLMs
par: Dwivedi, Ashutosh, et autres
Publié: (2025)

To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems
par: Chappidi, Shreya, et autres
Publié: (2026)

Using LLMs to identify features of personal and professional skills in an open-response situational judgment test
par: Walsh, Cole, et autres
Publié: (2025)

AccessEval: Benchmarking Disability Bias in Large Language Models
par: Panda, Srikant, et autres
Publié: (2025)

Gender Bias in Machine Translation and The Era of Large Language Models
par: Vanmassenhove, Eva
Publié: (2024)

Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models
par: Rao, Pooja S. B., et autres
Publié: (2025)

Large Language Models (LLMs) as Agents for Augmented Democracy
par: Gudiño-Rosero, Jairo, et autres
Publié: (2024)

The Price of Prompting: Profiling Energy Use in Large Language Models Inference
par: Husom, Erik Johannes, et autres
Publié: (2024)

Who Controls the Conversation? User Perspectives On Generative AI (LLM) System Prompts
par: Neumann, Anna, et autres
Publié: (2026)

Rethinking LLM Bias Probing Using Lessons from the Social Sciences
par: Morehouse, Kirsten N., et autres
Publié: (2025)

The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations
par: Salinas, Abel, et autres
Publié: (2023)

JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models
par: Wang, Ze, et autres
Publié: (2024)

BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
par: Xu, Xin, et autres
Publié: (2025)

Prompt Engineering Techniques for Mitigating Cultural Bias Against Arabs and Muslims in Large Language Models: A Systematic Review
par: Asseri, Bushra, et autres
Publié: (2025)

Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
par: Sakhawat, Adib, et autres
Publié: (2026)

Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach
par: Ko, Changgeon, et autres
Publié: (2024)

Prompt Selection Matters: Enhancing Text Annotations for Social Sciences with Large Language Models
par: Abraham, Louis, et autres
Publié: (2024)

LangFair: A Python Package for Assessing Bias and Fairness in Large Language Model Use Cases
par: Bouchard, Dylan, et autres
Publié: (2025)

Bias and Fairness in Large Language Models: A Survey
par: Gallegos, Isabel O., et autres
Publié: (2023)

Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play
par: Zeng, Yifan, et autres
Publié: (2024)

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias
par: Xu, Rongwu, et autres
Publié: (2024)

More is More: Addition Bias in Large Language Models
par: Santagata, Luca, et autres
Publié: (2024)

Should LLMs be WEIRD? Exploring WEIRDness and Human Rights in Large Language Models
par: Zhou, Ke, et autres
Publié: (2025)

Can LLMs Explain Themselves Counterfactually?
par: Dehghanighobadi, Zahra, et autres
Publié: (2025)

Dual-Metric Evaluation of Social Bias in Large Language Models: Evidence from an Underrepresented Nepali Cultural Context
par: Pandey, Ashish, et autres
Publié: (2026)

From Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship
par: Xu, Yue, et autres
Publié: (2025)

Towards Measuring and Modeling "Culture" in LLMs: A Survey
par: Adilazuarda, Muhammad Farid, et autres
Publié: (2024)

Perceived Political Bias in LLMs Reduces Persuasive Abilities
par: DiGiuseppe, Matthew, et autres
Publié: (2026)

Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications
par: Badhe, Sanket, et autres
Publié: (2026)

Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling
par: Wasi, Azmine Toushik, et autres
Publié: (2024)

A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions
par: Ranjan, Rajesh, et autres
Publié: (2024)

Automated Item Neutralization for Non-Cognitive Scales: A Large Language Model Approach to Reducing Social-Desirability Bias
par: Wu, Sirui, et autres
Publié: (2025)

Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models
par: Dudy, Shiran, et autres
Publié: (2025)

What's in a Name? Auditing Large Language Models for Race and Gender Bias
par: Salinas, Alejandro, et autres
Publié: (2024)

No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases
par: Chand, Shireen, et autres
Publié: (2025)

Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs
par: Wei, Kangda, et autres
Publié: (2025)