Imagen de Portada

Explaining How Quantization Disparately Skews a Model

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bellam, Abhimanyu, Kim, Jung-Eun
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computers and Society
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Aggregate Representation Measure for Predictive Model Reusability
por: Sangarya, Vishwesh, et al.
Publicado: (2024)

Learning Representational Disparities
por: Ravishankar, Pavan, et al.
Publicado: (2025)

Estimating Environmental Cost Throughout Model's Adaptive Life Cycle
por: Sangarya, Vishwesh, et al.
Publicado: (2024)

Superficial Safety Alignment Hypothesis
por: Li, Jianwei, et al.
Publicado: (2024)

Learning Disease Progression Models That Capture Health Disparities
por: Chiang, Erica, et al.
Publicado: (2024)

Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities
por: Farnadi, Golnoosh, et al.
Publicado: (2024)

Toward Fair Federated Learning under Demographic Disparities and Data Imbalance
por: Wu, Qiming, et al.
Publicado: (2025)

BaBE: Enhancing Fairness via Estimation of Latent Explaining Variables
por: Binkyte, Ruta, et al.
Publicado: (2023)

Learning-to-Explain through 20Q Gaming: An Explainable Recommender for Cybersecurity Education
por: Nusrat, Mary, et al.
Publicado: (2026)

FairFML: Fair Federated Machine Learning with a Case Study on Reducing Gender Disparities in Cardiac Arrest Outcome Prediction
por: Li, Siqi, et al.
Publicado: (2024)

FairTargetSim: An Interactive Simulator for Understanding and Explaining the Fairness Effects of Target Variable Definition
por: Gala, Dalia, et al.
Publicado: (2024)

Richer Output for Richer Countries: Uncovering Geographical Disparities in Generated Stories and Travel Recommendations
por: Bhagat, Kirti, et al.
Publicado: (2024)

Measuring Individual User Fairness with User Similarity and Effectiveness Disparity
por: Rampisela, Theresia Veronika, et al.
Publicado: (2026)

From Model Performance to Claim: How a Change of Focus in Machine Learning Replicability Can Help Bridge the Responsibility Gap
por: Kou, Tianqi
Publicado: (2024)

Let Me Try Again: Examining Replay Behavior by Tracing Students' Latent Problem-Solving Pathways
por: Zhang, Shan, et al.
Publicado: (2026)

AssurAI: Experience with Constructing Korean Socio-cultural Datasets to Discover Potential Risks of Generative AI
por: Lim, Chae-Gyun, et al.
Publicado: (2025)

How to be fair? A study of label and selection bias
por: Favier, Marco, et al.
Publicado: (2024)

Explainable AI Systems Must Be Contestable: Here's How to Make It Happen
por: Moreira, Catarina, et al.
Publicado: (2025)

KTCF: Actionable Recourse in Knowledge Tracing via Counterfactual Explanations for Education
por: Kim, Woojin, et al.
Publicado: (2026)

Evaluating Large Language Models for Fair and Reliable Organ Allocation
por: Kim, Brian Hyeongseok, et al.
Publicado: (2025)

Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach
por: Kwon, Soonwoo, et al.
Publicado: (2023)

From Protoscience to Epistemic Monoculture: How Benchmarking Set the Stage for the Deep Learning Revolution
por: Koch, Bernard J., et al.
Publicado: (2024)

Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency
por: Husom, Erik Johannes, et al.
Publicado: (2025)

Generative AI Policies under the Microscope: How CS Conferences Are Navigating the New Frontier in Scholarly Writing
por: Nahar, Mahjabin, et al.
Publicado: (2024)

GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
por: Patwardhan, Tejal, et al.
Publicado: (2025)

How Effective Is Constitutional AI in Small LLMs? A Study on DeepSeek-R1 and Its Peers
por: Menke, Antonio-Gabriel Chacón, et al.
Publicado: (2025)

Correlated Errors in Large Language Models
por: Kim, Elliot, et al.
Publicado: (2025)

Building a Domain-specific Guardrail Model in Production
por: Niknazar, Mohammad, et al.
Publicado: (2024)

Say My Name: a Model's Bias Discovery Framework
por: Ciranni, Massimiliano, et al.
Publicado: (2024)

The Amazon Nova Family of Models: Technical Report and Model Card
por: AGI, Amazon, et al.
Publicado: (2025)

From Model Training to Model Raising
por: Aydin, Roland, et al.
Publicado: (2025)

Corrigibility as a Singular Target: A Vision for Inherently Reliable Foundation Models
por: Potham, Ram, et al.
Publicado: (2025)

RESQUE: Quantifying Estimator to Task and Distribution Shift for Sustainable Model Reusability
por: Sangarya, Vishwesh, et al.
Publicado: (2024)

iScore: Visual Analytics for Interpreting How Language Models Automatically Score Summaries
por: Coscia, Adam, et al.
Publicado: (2024)

How Far Are We From AGI: Are LLMs All We Need?
por: Feng, Tao, et al.
Publicado: (2024)

Training Foundation Models as Data Compression: On Information, Model Weights and Copyright Law
por: Franceschelli, Giorgio, et al.
Publicado: (2024)

Towards Sustainability Model Cards
por: Jouneaux, Gwendal, et al.
Publicado: (2025)

Sabotage Evaluations for Frontier Models
por: Benton, Joe, et al.
Publicado: (2024)

Foundation Model Transparency Reports
por: Bommasani, Rishi, et al.
Publicado: (2024)

Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods
por: Olesen, Vincent, et al.
Publicado: (2024)