New AI error correctors improve classifier performance with provable guarantees.
problem Improving AI classifier performance with scarce training data.
method Weakly supervised AI error correctors with performance guarantees.
result Provable performance guarantees for AI error correction.
Improved AI patent classifier measures U.S. and China's AI patenting.
problem Measuring AI patents with high precision and generalization.
method Fine-tuning PatentSBERTa on manually labeled data from USPTO's AI Patent Dataset.
result Rapid growth in AI patenting in both countries, but different organizational patterns.
Mathematical conditions and practical computations for adversarial robustness measures are established.
problem Existence, uniqueness, and scalability of adversarial robustness measures for AI classifiers.
method Formulated and proven mathematical conditions for existence, uniqueness, and explicit analytical computation of minimal adversarial paths and distances. Practical computation demonstrated on various AI tools and synthetic benchmarks.
result Explicit mathematical conditions and practical computations for adversarial robustness measures are established.
New AI stock indices classify firms' AI engagement using 10-K filings.
problem Opaque AI selection criteria in existing ETFs.
method NLP analysis of 10-K filings to classify AI stocks.
result Companies with higher AI engagement have greater positive returns.
Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we present a simple hypothesis about a feature compression property of artificial i…
Unified Uncertainty Calibration improves AI predictions by combining different types of uncertainty.
problem AI classifiers struggle with uncertainty, leading to miscalibrated predictions and poor performance.
method Unified Uncertainty Calibration (U2C) combines aleatoric and epistemic uncertainties to improve prediction quality.
result U2C outperforms traditional reject-or-classify methods across various ImageNet benchmarks.
Paper explains distance-based classifiers using neural network structures.
problem Making distance-based classifiers explainable.
method Uncovering latent neural network structures in distance-based classifiers.
result Novel explanation approach outperforms baselines.
Study reveals AI skin cancer classifiers underperform for darker skin phototypes, advocating for fairness auditing.
problem AI bias in dermatology, particularly for darker skin phototypes.
method Predictive Representativity (PR) framework, evaluating classifiers on HAM10000 and BOSQUE Test sets.
result Substantial performance disparities by skin phototype, highlighting AI bias.
Classifier-based AI safety gates fail in self-improvement, even with advanced verification methods.
problem Maintaining reliable oversight of AI systems as they improve over iterations.
method Comprehensive empirical testing on neural controllers and MuJoCo benchmarks, using various classifiers and verification methods.
result Classifier-based safety gates fail in maintaining reliable oversight, even with advanced verification methods.
FinAI-BERT classifies AI disclosures in financial reports with high accuracy.
problem Systematic detection of AI-related disclosures in financial reports.
method Fine-tuned transformer-based model on a curated dataset.
result Achieved near-perfect classification performance (99.37% accuracy).
This paper reviews metrics to assess AI model calibration accuracy.
problem AI model probabilities do not always match their true accuracy.
method Comprehensive review of 82 probability calibration metrics.
result Identified 4 classifier families and 1 object detection family of metrics.
In order to study the application of artificial intelligence (AI) to dental imaging, we applied AI technology to classify a set of panoramic radiographs using (a) a convolutional neural network (CNN) which is a form of an artificial neural network (ANN), (b) representative image cognition algorithms that implement scal…
AI techniques explain synthetic tabular data weaknesses.
problem Challenges in evaluating synthetic tabular data quality.
method Apply explainable AI to a binary detection classifier.
result Reveals inconsistencies, unrealistic dependencies, or missing patterns in synthetic data.
Unified framework for intersectionally fair AI models using MIO.
problem Bias in AI models for high-risk domains.
method Mixed-Integer Optimization (MIO) for fairness and interpretability.
result Improved performance in detecting and mitigating bias at intersections.
We employ techniques of machine-learning, exemplified by support vector machines and neural classifiers, to initiate the study of whether AI can "learn" algebraic structures. Using finite groups and finite rings as a concrete playground, we find that questions such as identification of simple groups by "looking" at the…
AI system narrows human decision options for better outcomes.
problem Improving human decision-making in sequential tasks.
method Developed a decision support system using a pre-trained AI agent to limit human action choices.
result Participants outperformed AI and solo play in a wildfire mitigation game.
Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and interpreting inputs from humans. In contrast, inputs created by humans are often treated as a given. We investigate how inputs of humans can…
ALPODS AI diagnoses high-dimensional biomedical data with human-understandable explanations.
problem AI decisions in high-dimensional biomedical data are not explainable to humans.
method ALPODS method classifies data based on clusters and generates fuzzy reasoning rules.
result ALPODS provides understandable explanations for AI diagnoses.
The paper compares ML models for credit scoring and investment decisions using explainable AI.
problem The opacity of machine learning models in financial services.
method Comparison of various machine learning models (single classifiers, ensembles, neural networks) and explainability techniques (LIME, SHAP).
result Ensemble classifiers and neural networks outperform in credit scoring models.
timeXplain bridges AI and time series, making predictions understandable.
problem Making time series classifier predictions interpretable.
method Developed a framework that combines time series data with model-agnostic explainers.
result timeXplain improves the interpretability of time series classifiers.
This work proposes external correctors for quick AI error corrections without system modification.
problem Quick corrections of AI errors without modifying legacy systems.
method Special `external` devices with classifiers for high-dimensional data.
result Simple classifiers can correct small errors in high-dimensional data.
New method explains high-dimensional text classifiers.
problem Limited explainability tools for high-dimensional inputs and neural networks.
method Theoretical high-dimensional properties in neural networks.
result Improved explainability for neural network classifiers.
To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to specifying complex goals asks humans to judge during training which agent behaviors are safe and useful, but this approach can fail if the task is too complicated for a human to…
AI models predict stock trends using historical data and public sentiment.
problem Improving stock market prediction accuracy using AI.
method Employed regression and classification ML algorithms for technical and fundamental analysis respectively.
result Median performance suggests AI is not yet superior to stock markets.
Artificial Intelligence (AI) systems sometimes make errors and will make errors in the future, from time to time. These errors are usually unexpected, and can lead to dramatic consequences. Intensive development of AI and its practical applications makes the problem of errors more important. Total re-engineering of the…
This review clarifies XAI for regression models and establishes new theoretical insights.
problem Lack of XAI techniques for regression models, especially in safety-critical applications.
method Clarifies conceptual differences, establishes theoretical insights, provides demonstrations, discusses challenges.
result Novel theoretical insights and demonstrations of XAI for regression models.
The paper introduces sanity tests to detect spurious correlations in AI-guided radiology systems.
problem Detecting when AI systems perform well on development data for the wrong reasons.
method Design and implementation of sanity tests to identify spurious correlations.
result Sanity tests can identify spurious correlations in AI-guided radiology systems.
Interpretable ML models for missing data and visualisation.
problem Understanding and evaluating fairness in ML models.
method Introduced angle-based variants of Learning Vector Quantization (LVQ) models.
result Models can handle missing values and extract knowledge from datasets.
AI progress measured by reduced compute needed to reach past performance.
problem Quantifying algorithmic progress in AI.
method Analysis of floating-point operations required to train neural networks.
result Algorithmic efficiency doubled every 16 months over 7 years.
AI agent predicts industry and product/service codes for companies.
problem Manual curation of company data is expensive and prone to errors.
method Hierarchical multi-class industry code classifier with multi-label product/service code classifier.
result High accuracy (92-96%) achieved with limited labeled data.
AI models assess psychological risks in currency trading.
problem Identifying psychological risks in currency traders.
method Developed a decision tree model to identify patterns in historical data.
result Enhanced decision-making through real-time alerts.
Study improves prediction of UK road accidents' severity using AI.
problem Improving prediction of UK road traffic accident severity.
method Combination of machine learning, econometric, and statistical methods on historical data.
result XGBoost model with RMSE of 0.176 and MAE of 0.087 outperforms naive forecasting.
AI classifies tourist events for better service.
problem Classifying tourist events efficiently across diverse sources.
method CRISP-DM, supervised machine learning, NLP.
result Automatic classification tool for consistent event catalogs.
This paper improves deep learning classifiers by integrating conformal prediction during training.
problem High-stake AI applications require reliable uncertainty estimates for safe deployment.
method Integrates conformal prediction (CP) during training of deep learning models.
result Reduces inefficiency and allows more control over confidence sets.
CoE modularizes LLMs for scalable, cost-effective AI systems.
problem Challenges in scalability, cost, and customization of monolithic LLMs.
method Composition of Experts (CoE) leverages multiple expert LLMs with a router for dynamic selection.
result CoE achieves superior performance with reduced computational overhead and cost.
Interprets AI model for identifying boosted H → b̄b jets.
problem Difficulty in explaining AI model decisions due to complexity.
method Exploring Interaction Network (IN) model and Neural Activation Pattern (NAP) diagrams.
result NAP diagrams reveal important information about hidden layers' activity.
A new L2D system produces calibrated probabilities of expert correctness without sacrificing accuracy.
problem Calibration of learning to defer systems for safety.
method One-vs-all classifiers with a consistent surrogate loss function.
result Proposes a calibrated L2D system that outperforms existing methods in accuracy and calibration.
Survey of neurosymbolic AI methods for reasoning over knowledge graphs.
problem Combining symbolic reasoning with deep learning for graph data.
method Logically-informed embedding, embedding with logical constraints, and rule learning approaches.
result A novel taxonomy for classifying neurosymbolic reasoning methods on knowledge graphs.
Study compares AI models for stock price prediction using financial news.
problem Predicting stock price movements using financial news.
method Used FinBERT, GPT-4, and Logistic Regression for sentiment analysis and prediction.
result Logistic Regression outperformed FinBERT and GPT-4, achieving 81.83% accuracy.
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, understanding when a classifier's predictions should and should not be trusted has received …
A recently introduced text classifier, called SS3, has obtained state-of-the-art performance on the CLEF's eRisk tasks. SS3 was created to deal with risk detection over text streams and, therefore, not only supports incremental training and classification but also can visually explain its rationale. However, little att…
The paper uses AI to analyze on-chain parameters and identify risky cryptocurrencies.
problem Identifying risky cryptocurrencies and understanding their price factors.
method Historical data analysis, AI algorithms, clustering, classification.
result A significant negative correlation between cryptocurrency price and maximum and total supply, and a weak positive correlation with 24-hour trading volume.
Geometric framework detects concept frustration between human concepts and machine representations.
problem Aligning human concepts with machine learning representations.
method Geometric framework and similarity measures for detecting concept frustration.
result Concept frustration affects machine learning model performance and reorganizes learned concept representations.
The paper addresses the difficulty of decision makers trusting AI-assisted predictions and proposes a method to improve confidence values.
problem Decision makers struggle to trust AI-assisted predictions based on confidence values.
method The paper investigates why decision makers have difficulties and proposes a method to construct more useful confidence values.
result Multicalibration with respect to the decision maker's confidence on her own predictions is a sufficient condition for alignment, leading to better decisions.
Paper introduces Native Guide for generating time series counterfactual explanations.
problem Lack of explainability for time series data in AI systems.
method Model-agnostic, instance-based counterfactual generation for time series classification.
result Native Guide produces better counterfactual explanations than benchmarks.
Proposes a method to ensure accurate estimation of rare events in AI systems.
problem Lack of efficiency guarantees in black-box systems for rare-event simulation.
method Integrates deep learning with importance sampling to create a statistically guaranteed estimator.
result Demonstrates effective estimation of rare-event probabilities in AI systems.
Benchmark evaluates AI-generated financial QA hallucinations, highlighting system vulnerabilities.
problem Ensuring factual accuracy of AI-generated financial QA outputs.
method Developed a benchmark dataset and evaluated six detection methods under clean and noisy conditions.
result LLM-based judges and embedding methods perform best, but degrade under noisy conditions.
Improved AI lung ultrasound segmentation using expert confidence values.
problem Label uncertainty in lung ultrasound due to subjective interpretation by radiologists.
method Designing a data annotation protocol capturing expert confidence, training AI on binarized labels with confidence thresholds.
result Improved AI segmentation and better clinical outcomes (e.g., S/F oxygenation ratio estimation, patient readmission prediction).