Imagen de Portada

Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shan, Zhengyang, Mueller, Aaron
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge
por: Yin, Maxwell J., et al.
Publicado: (2024)

Obscured but Not Erased: Evaluating Nationality Bias in LLMs via Name-Based Bias Benchmarks
por: Pelosio, Giulio, et al.
Publicado: (2025)

Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
por: Wang, Huazheng, et al.
Publicado: (2025)

In-Context Learning Without Copying
por: Sahin, Kerem, et al.
Publicado: (2025)

RedacBench: Can AI Erase Your Secrets?
por: Jeon, Hyunjun, et al.
Publicado: (2026)

Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
por: Ahsan, Hiba, et al.
Publicado: (2025)

Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks
por: Mueller, Aaron
Publicado: (2024)

Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
por: Nikankin, Yaniv, et al.
Publicado: (2024)

Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
por: Cheng, Yinjie, et al.
Publicado: (2025)

Assessing the Reliability of LLMs Annotations in the Context of Demographic Bias and Model Explanation
por: Mohammadi, Hadi, et al.
Publicado: (2025)

Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models
por: Hanna, Michael, et al.
Publicado: (2024)

Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias
por: Tonneau, Manuel, et al.
Publicado: (2026)

Demographic and Linguistic Bias Evaluation in Omnimodal Language Models
por: Elobaid, Alaa
Publicado: (2026)

Order-Independence Without Fine Tuning
por: McIlroy-Young, Reid, et al.
Publicado: (2024)

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
por: Chandna, Bhavik, et al.
Publicado: (2025)

Gender Inclusivity Fairness Index (GIFI): A Multilevel Framework for Evaluating Gender Diversity in Large Language Models
por: Shan, Zhengyang, et al.
Publicado: (2025)

LLMs Do Not See Age: Assessing Demographic Bias in Automated Systematic Review Synthesis
por: Aghaebe, Favour Yahdii, et al.
Publicado: (2025)

A Novel Method to Metigate Demographic and Expert Bias in ICD Coding with Causal Inference
por: Zhang, Bin, et al.
Publicado: (2024)

Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information
por: Iskander, Shadi, et al.
Publicado: (2024)

Analysing Moral Bias in Finetuned LLMs through Mechanistic Interpretability
por: Raimondi, Bianca, et al.
Publicado: (2025)

Eliminating Position Bias of Language Models: A Mechanistic Approach
por: Wang, Ziqi, et al.
Publicado: (2024)

Trustworthy Social Bias Measurement
por: Bommasani, Rishi, et al.
Publicado: (2022)

Erasing Conceptual Knowledge from Language Models
por: Gandikota, Rohit, et al.
Publicado: (2024)

Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics
por: Alizadeh, Meysam, et al.
Publicado: (2025)

Does the Prompt-based Large Language Model Recognize Students' Demographics and Introduce Bias in Essay Scoring?
por: Yang, Kaixun, et al.
Publicado: (2025)

Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study
por: Majumdar, Ayan, et al.
Publicado: (2025)

The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendations
por: Salinas, Abel, et al.
Publicado: (2023)

Reasoning Models Can Be Effective Without Thinking
por: Ma, Wenjie, et al.
Publicado: (2025)

Sometimes the Model doth Preach: Quantifying Religious Bias in Open LLMs through Demographic Analysis in Asian Nations
por: Shankar, Hari, et al.
Publicado: (2025)

Characterizing the Role of Similarity in the Property Inferences of Language Models
por: Rodriguez, Juan Diego, et al.
Publicado: (2024)

Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections
por: Mastromichalakis, Orfeas Menis, et al.
Publicado: (2025)

Bias in News Summarization: Measures, Pitfalls and Corpora
por: Steen, Julius, et al.
Publicado: (2023)

UniErase: Towards Balanced and Precise Unlearning in Language Models
por: Yu, Miao, et al.
Publicado: (2025)

How to Evaluate Automatic Speech Recognition: Comparing Different Performance and Bias Measures
por: Patel, Tanvina, et al.
Publicado: (2025)

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning
por: Ma, Chuang, et al.
Publicado: (2026)

Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models
por: Zhou, Hanhan, et al.
Publicado: (2026)

Who Gets Which Message? Auditing Demographic Bias in LLM-Generated Targeted Text
por: Islam, Tunazzina
Publicado: (2026)

Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages
por: Brinkmann, Jannik, et al.
Publicado: (2025)

In-context Learning Generalizes, But Not Always Robustly: The Case of Syntax
por: Mueller, Aaron, et al.
Publicado: (2023)

Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases
por: Gao, Bufan, et al.
Publicado: (2025)