paper-with-me

홈 › Papers

AI Biases as Asymmetries: A Review to Guide Practice

2025-03-10 · Gabriella Waters, Phillip Honenberger

The understanding of bias in AI is currently undergoing a revolution. Initially understood as errors or flaws, biases are increasingly recognized as integral to AI systems and sometimes preferable to less biased alternatives. In this paper, we review the reasons for this changed understanding and provide new guidance on two questions: First, how should we think about and measure biases in AI systems, consistent with the new understanding? Second, what kinds of bias in an AI system should we accept or even amplify, and what kinds should we minimize or eliminate, and why? The key to answering both questions, we argue, is to understand biases as "violations of a symmetry standard" (following Kelly). We distinguish three main types of asymmetry in AI systems-error biases, inequality biases, and process biases-and highlight places in the pipeline of AI development and application where bias of each type is likely to be good, bad, or inevitable.

📄 PDF Abstract BibTeX arXiv:2503.07326

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Are Non-English Papers Reviewed Fairly? Language-of-Study Bias in NLP Peer Reviews

2026-04-08 · Ehsan Barkhordar, Abdulfattah Safa, Verena Blaschke, Erika Lombart 외 arxiv

Peer review plays a central role in the NLP publication process, but is susceptible to various biases. Here, we study language-of-study (LoS) bias: the tendency for reviewers to evaluate a paper differently based on the …

Best Practices for Responsible Machine Learning in Credit Scoring

2024-09-30 · Giovani Valdrighi, Athyrson M. Ribeiro, Jansen S. B. Pereira, Vitoria Guardieiro 외

The widespread use of machine learning in credit scoring has brought significant advancements in risk assessment and decision-making. However, it has also raised concerns about potential biases, discrimination, and lack …

Decision MakingFairnessSystematic Literature Review

Probing Social Identity Bias in Chinese LLMs with Gendered Pronouns and Social Groups

2025-10-08 · Geng Liu, Feng Li, Junjie Mu, Mengxiao Zhu 외 arxiv

Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns that they may reflect and amplify social biases. We investigate social identity biases in Chinese LLMs using Mandarin-s…

Co-clustering for directed graphs: the Stochastic co-Blockmodel and spectral algorithm Di-Sim

2012-04-10 · Karl Rohe, Tai Qin, Bin Yu

Directed graphs have asymmetric connections, yet the current graph clustering methodologies cannot identify the potentially global structure of these asymmetries. We give a spectral algorithm called di-sim that builds on…

ClusteringGraph Clustering

Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review

2025-02-18 · Jiatao Li, Yanheng Li, Xinyu Hu, Mingqi Gao 외

We propose an aspect-guided, multi-level perturbation framework to evaluate the robustness of Large Language Models (LLMs) in automated peer review. Our framework explores perturbations in three key components of the pee…