English
Related papers

Related papers: When AAA Satisfies Nothing: Impossibility Theorems…

200 papers

Ranked decision systems -- recommenders, ad auctions, clinical triage queues -- must decide when to intervene in ranked outputs and when to abstain. We study when confidence-based abstention monotonically improves decision quality, and when…

Artificial Intelligence · Computer Science 2026-03-11 Ronald Doku

Explainable Artificial Intelligence (XAI) methods (SHAP, LIME) are increasingly adopted to interpret models in high-stakes businesses. However, the credibility of these explanations, their stability under realistic data perturbations,…

Artificial Intelligence · Computer Science 2026-03-06 Alin-Gabriel Vaduva , Simona-Vasilica Oprea , Adela Bara

We show that lenders face more uncertainty when assessing default risk of historically under-served groups in US credit markets and that this information disparity is a quantitatively important driver of inefficient and unequal credit…

General Economics · Economics 2021-05-18 Laura Blattner , Scott Nelson

This paper studies the identification, estimation, and hypothesis testing problem in complete and incomplete economic models with testable assumptions. Testable assumptions ($A$) give strong and interpretable empirical content to the models…

Econometrics · Economics 2022-03-11 Moyu Liao

As financial institutions increasingly adopt machine learning for credit risk assessment, the persistence of algorithmic bias remains a critical barrier to equitable financial inclusion. This study provides a comprehensive audit of…

Machine Learning · Computer Science 2026-01-27 Navya SD , Sreekanth D , SS Uma Sankari

Knowing when a classifier's prediction can be trusted is useful in many applications and critical for safely using AI. While the bulk of the effort in machine learning research has been towards improving classifier performance,…

Machine Learning · Statistics 2018-10-30 Heinrich Jiang , Been Kim , Melody Y. Guan , Maya Gupta

No feature ranking can be simultaneously faithful, stable, and complete when features are collinear. For collinear pairs, ranking reduces to a coin flip. We prove this impossibility, quantify it for four model classes, resolve it via…

Machine Learning · Computer Science 2026-05-22 Drake Caraker , Bryan Arnold , David Rhoads

We argue that formal certification of AI alignment over open-ended or unbounded input domains is impossible under standard assumptions in computational complexity and learning theory, and characterise what remains achievable. Two…

Machine Learning · Statistics 2026-05-28 Ayushi Agarwal

A well-known limitation of AI systems is presumptuousness: the tendency of AI systems to provide confident answers when information may be lacking. This challenge is particularly acute in legal applications, where a core task for attorneys,…

Artificial Intelligence · Computer Science 2026-04-23 Mohamed Afane , Emily Robitschek , Derek Ouyang , Daniel E. Ho

This paper investigates the application of machine learning when training a credit decision model over real, publicly available data whilst accounting for "bias objectives". We use the term "bias objective" to describe the requirement that…

Machine Learning · Computer Science 2021-10-26 Nigel Kingsman

Machine learning models are often used to decide who receives a loan, a job interview, or a public benefit. Models in such settings use features without considering their actionability. As a result, they can assign predictions that are…

Machine Learning · Computer Science 2024-05-02 Avni Kothari , Bogdan Kulynych , Tsui-Wei Weng , Berk Ustun

Explanations of the replication crisis often emphasize misconduct, questionable research practices, or incentive misalignment, implying that behavioral reform is sufficient. This paper argues that a substantial component is architectural:…

Methodology · Statistics 2026-03-05 Marco Pollanen

Development funds are essential to finance climate change adaptation and are thus an important part of international climate policy. % However, the absence of a common reporting practice makes it difficult to assess the amount and…

Computers and Society · Computer Science 2022-12-01 Janos Borst , Thomas Wencker , Andreas Niekler

The Uniform Appraisal Dataset (UAD) 3.6's mandatory 2026 implementation transforms residential property valuation from narrative reporting to structured, machine-readable formats. This paper provides the first comprehensive analysis of this…

Computers and Society · Computer Science 2025-08-06 Petteri Teikari , Mike Jarrell , Maryam Azh , Harri Pesola

Statistical modeling can involve a tension between assumptions and statistical identification. The law of the observable data may not uniquely determine the value of a target parameter without invoking a key assumption, and, while…

Methodology · Statistics 2022-12-06 Paul Gustafson

Among the various aspects of algorithmic fairness studied in recent years, the tension between satisfying both \textit{sufficiency} and \textit{separation} -- e.g. the ratios of positive or negative predictive values, and false positive or…

Machine Learning · Computer Science 2022-05-26 Limor Gultchin , Vincent Cohen-Addad , Sophie Giffard-Roisin , Varun Kanade , Frederik Mallmann-Trenn

An auditor instructs an AI assistant: "open each file individually using the Read tool -- no scripts, no agents." The AI replies "Yes" -- then issues a single batched call summarizing all fifty files at once. We call this the Compliance…

Computation and Language · Computer Science 2026-05-05 Kwan Soo Shin

Complex decision-making is a prominent aspect of Requirements Engineering. This work presents the Bayesian network Requisites that predicts whether the requirements specification documents have to be revised. We show how to validate…

Software Engineering · Computer Science 2024-01-24 J. del Sagrado , I. M. del Águila

An agent is a misspecified Bayesian if she updates her belief using Bayes' rule given a subjective, possibly misspecified model of her signals. This paper shows that a belief sequence is consistent with misspecified Bayesian updating if and…

Theoretical Economics · Economics 2026-03-25 Pooya Molavi

The rapid integration of AI into education has prioritized capability over trustworthiness, creating significant risks. Real-world deployments reveal that even advanced models are insufficient without extensive architectural scaffolding to…

Computers and Society · Computer Science 2026-01-13 Abu Syed
‹ Prev 1 2 3 10 Next ›