Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shan, Zhengyang, Mueller, Aaron
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Trustworthy Social Bias Measurement
by: Bommasani, Rishi, et al.
Published: (2022)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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