Leveraging Prototypical Representations for Mitigating Social Bias without Demographic Information

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Iskander, Shadi, Radinsky, Kira, Belinkov, Yonatan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Computers and Society Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Fair Representation in Parliamentary Summaries: Measuring and Mitigating Inclusion Bias
di: Cunningham, Eoghan, et al.
Pubblicazione: (2025)

Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias
di: Itzhak, Itay, et al.
Pubblicazione: (2023)

DSO: Direct Steering Optimization for Bias Mitigation
di: Paes, Lucas Monteiro, et al.
Pubblicazione: (2025)

Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation
di: Vargas, Francisco, et al.
Pubblicazione: (2020)

Mitigating Bias for Question Answering Models by Tracking Bias Influence
di: Ma, Mingyu Derek, et al.
Pubblicazione: (2023)

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

Intrinsic Meets Extrinsic Fairness: Assessing the Downstream Impact of Bias Mitigation in Large Language Models
di: Arzaghi', 'Mina, et al.
Pubblicazione: (2025)

BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
di: Xu, Xin, et al.
Pubblicazione: (2025)

Fast Forwarding Low-Rank Training
di: Rahamim, Adir, et al.
Pubblicazione: (2024)

SAEs Are Good for Steering -- If You Select the Right Features
di: Arad, Dana, et al.
Pubblicazione: (2025)

Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs
di: Itzhak, Itay, et al.
Pubblicazione: (2025)

Beyond Behaviorist Representational Harms: A Plan for Measurement and Mitigation
di: Chien, Jennifer, et al.
Pubblicazione: (2024)

Silent Tokens, Loud Effects: Padding in LLMs
di: Himelstein, Rom, et al.
Pubblicazione: (2025)

Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
di: Hanna, Michael, et al.
Pubblicazione: (2024)

Fairness-Aware Graph Representation Learning with Limited Demographic Information
di: Wang, Zichong, et al.
Pubblicazione: (2025)

GG-BBQ: German Gender Bias Benchmark for Question Answering
di: Satheesh, Shalaka, et al.
Pubblicazione: (2025)

Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds
di: Abels, Axel, et al.
Pubblicazione: (2025)

LIBRA: Measuring Bias of Large Language Model from a Local Context
di: Pang, Bo, et al.
Pubblicazione: (2025)

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space
di: Katz, Shahar, et al.
Pubblicazione: (2024)

From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs
di: Itzhak, Itay, et al.
Pubblicazione: (2026)

Representation Bias of Adolescents in AI: A Bilingual, Bicultural Study
di: Wolfe, Robert, et al.
Pubblicazione: (2024)

The ProLiFIC dataset: Leveraging LLMs to Unveil the Italian Lawmaking Process
di: Contestabile, Matilde, et al.
Pubblicazione: (2025)

Addressing Stereotypes in Large Language Models: A Critical Examination and Mitigation
di: Kazi, Fatima
Pubblicazione: (2025)

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
di: Prakash, Nikhil, et al.
Pubblicazione: (2024)

Leveraging Social Determinants of Health in Alzheimer's Research Using LLM-Augmented Literature Mining and Knowledge Graphs
di: Shang, Tianqi, et al.
Pubblicazione: (2024)

Unintended Impacts of LLM Alignment on Global Representation
di: Ryan, Michael J., et al.
Pubblicazione: (2024)

Representation Surgery: Theory and Practice of Affine Steering
di: Singh, Shashwat, et al.
Pubblicazione: (2024)

Interpreting Latent Student Knowledge Representations in Programming Assignments
di: Fernandez, Nigel, et al.
Pubblicazione: (2024)

Quality Matters: Evaluating Synthetic Data for Tool-Using LLMs
di: Iskander, Shadi, et al.
Pubblicazione: (2024)

The Geometric Price of Discrete Logic: Context-driven Manifold Dynamics of Number Representations
di: Zhang, Long, et al.
Pubblicazione: (2026)

ContraSim -- Analyzing Neural Representations Based on Contrastive Learning
di: Rahamim, Adir, et al.
Pubblicazione: (2023)

A Representation-Level Assessment of Bias Mitigation in Foundation Models
di: Nizhnichenkov, Svetoslav, et al.
Pubblicazione: (2026)

From Representational Harms to Quality-of-Service Harms: A Case Study on Llama 2 Safety Safeguards
di: Chehbouni, Khaoula, et al.
Pubblicazione: (2024)

Mitigating Social Desirability Bias in Random Silicon Sampling
di: Chapala, Sashank, et al.
Pubblicazione: (2025)

Breaking Down Bias: On The Limits of Generalizable Pruning Strategies
di: Ma, Sibo, et al.
Pubblicazione: (2025)

Bias and Fairness in Large Language Models: A Survey
di: Gallegos, Isabel O., et al.
Pubblicazione: (2023)

Social Determinants of Health Prediction for ICD-9 Code with Reasoning Models
di: Khan, Sharim, et al.
Pubblicazione: (2025)

Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networks
di: Azumah, Sylvia Worlali, et al.
Pubblicazione: (2024)

Toward Automated Detection of Biased Social Signals from the Content of Clinical Conversations
di: Chen, Feng, et al.
Pubblicazione: (2024)