Proposes a new trust framework for AI models to maximize utility.
problem Concerns over bias and discrimination in predictive models.
method Introduces a novel trust framework inspired by philosophy, focusing on maximizing Bayes utility.
result Properly-ranked models are inherently U-trustworthy. Paper quarantines unreliable Yelp users by detecting review spam.
problem Unreliable and spamming users deceive Yelp's users.
method Used RSD and spam detection techniques on key features.
result More than 80% of Yelp's accounts are unreliable, and highly-rated businesses are often spammed.
User strategization undermines algorithmic trustworthiness.
problem User strategic behavior corrupts algorithmic data and trust.
method Modeling user-platform interactions as a game, analyzing strategic behavior's short-term benefits and long-term harms.
result User strategization can initially benefit platforms but ultimately harms their ability to make accurate decisions.
Efficient approach improves prediction calibration for domain shifts.
problem Improving uncertainty-aware predictions for domain shifts.
method Combining entropy-encouraging and adversarial calibration losses.
result Substantially outperforms existing approaches in domain drift calibration.
New holistic approach measures sample-level adversarial vulnerability for trustworthy systems.
problem Inherent bias in adversarial attacks across subgroups.
method Combining high-frequency feature reliance and sample-distance to decision boundary.
result Holistic approach improves adversarial vulnerability estimation and system trustworthiness.
AI systems need reliable testing to ensure safety and trustworthiness.
problem Current AI Act lacks functional trustworthiness for AI systems.
method Define technical application distribution, set risk-based performance, and conduct statistically valid testing.
result Reliable functional trustworthiness is essential for AI systems.
This work improves neural network trustworthiness through uncertainty estimation.
problem Overconfident neural networks lead to poor performance under distribution shifts.
method Develops a general uncertainty framework for neural networks, including classification with rejection.
result Improves model trustworthiness and robustness in decision-making tasks.
Study shows trust and trustworthiness emerge through reinforcement learning.
problem Trust and trustworthiness are universal but not predicted by traditional economic models.
method Used Q-learning algorithm to simulate trust and trustworthiness dynamics in a trust game.
result High levels of trust and trustworthiness emerge when individuals consider both past and future experiences.
Develops methods for AI self-assessment to improve trustworthiness.
problem Uncertainty in AI predictions and lack of trust in AI systems.
method Uncertainty estimation techniques considering practical impacts and costs.
result Guidelines for selecting and designing effective AI self-assessment methods.
Conformal Alignment ensures trustworthy outputs from foundation models.
problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.
PolicySynth improves synthetic data alignment with real data for better campaign decisions.
problem Synthetic data used in decision support systems often leads to incorrect decisions.
method PolicySynth framework that conditions synthetic data on churn scorer to align with real data decisions.
result PolicySynth achieves high strategy simulation fidelity (0.923-0.960) on churn and acquisition datasets.
The Intensive Care Unit (ICU) is a hospital department where machine learning has the potential to provide valuable assistance in clinical decision making. Classical machine learning models usually only provide point-estimates and no uncertainty of predictions. In practice, uncertain predictions should be presented to …
A framework assesses the trustworthiness of probabilistic classifiers using local calibration error.
problem Assessing the trustworthiness of probabilistic classifiers beyond traditional metrics.
method I-trustworthy framework linking local calibration to trustworthiness; Kernel Local Calibration Error (KLCE) method for hypothesis testing.
result The effectiveness of the proposed test statistic demonstrated through simulated and real-world datasets.
MCD offers a complete model understanding for high-stake decisions.
problem Local model understanding in XAI methods is not sufficient for high-stake decisions.
method MCD extends concept-based methods to ensure global model understanding via multi-dimensional subspaces.
result MCD provides a complete model understanding, ensuring the model reasoning is related to the actual model.
A new method reduces data valuation variance for more trustworthy data trading.
problem Data valuation and trustworthy data trading in algorithmic prediction.
method Variance reduced Shapley value estimation using stratified sampling.
result VRDS method reduces estimation variance and improves data marketplace development.
Study improves summarization reliability in risky scenarios.
problem Reliability of automatic summarization in high-risk contexts.
method Conditional generation with Bayesian inference and entropy regularization.
result Significant improvement in robustness and reliability of summarization.
Wrapper improves black-box model auditability and decision trustworthiness.
problem Lack of transparency and auditability in machine learning models used in complex applications.
method Integrates uncertainty measures into black-box models to enhance auditability and decision trustworthiness.
result Improves trust in machine learning models by providing actionable mechanisms to reject uncertain predictions.
Neural approach enhances AI trustworthiness, generalization, and robustness.
problem Challenges in explaining, generalizing, and adapting AI models to uncertain environments.
method Customized trustworthy networks, flexible learning regularizers, open-world recognition losses.
result Significant performance improvements across various open-world multimedia recognition scenarios.
New calibration measure SCDL improves trust in AI predictions.
problem Improving trust in AI predictions by ensuring they are both actionable and testable.
method Introducing SCDL, a new calibration measure that is fully actionable and testable.
result SCDL is the first calibration measure that is fully actionable and testable.
Bayesian meta learning improves uncertainty quantification in regression.
problem Trusting uncertainty quantification in Bayesian regression.
method Trust-Bayes framework for Bayesian meta learning, optimizing for trustworthy uncertainty quantification.
result Lower bounds and sample complexity for trustworthy uncertainty quantification are characterized.
PiNets provide faithful explanations for neural networks.
problem Lack of true explanations for neural network predictions.
method Pointwise-interpretable Networks (PiNets) that form linear models instance-wise.
result PiNets offer explanations that are meaningful, aligned, robust, and sufficient.
DeFi TrustBoost uses blockchain and AI to assess small business loans.
problem Assessing small business loans from low-wealth households.
method Combines blockchain and Explainable AI to ensure confidentiality, compliance, and security.
result Tamper-proof auditing and on-chain/off-chain data storage for financial organizations.
Study identifies negative data externalities affecting model performance on specific groups.
problem Negative data externalities on group performance in machine learning models.
method Characterized and detected data-model inefficiencies, focusing on specific types of externalities.
result Negative data externalities can lower model performance on specific sub-groups, even with larger datasets.
The paper connects decision tree interpretability and robustness through separation.
problem Empirical observation of a connection between robustness and interpretability in decision trees.
method Investigation of the connection through decision trees and l∞-perturbation robustness, proving bounds on tree size. result First algorithm with guarantees on robustness, interpretability, and accuracy for decision trees.
Online knowledge repositories typically rely on their users or dedicated editors to evaluate the reliability of their content. These evaluations can be viewed as noisy measurements of both information reliability and information source trustworthiness. Can we leverage these noisy evaluations, often biased, to distill a…
Glitches cause unreliable AI decisions with steep boundaries.
problem Glitches impair the reliability of AI models with steep decision boundaries.
method Formal definition of glitches, algorithmic search using MILP encoding.
result Glitches are widespread and indicate potential model inconsistencies.
Optimizes calibration error estimators for better classifier trustworthiness.
problem Lack of guidance on selecting and tuning calibration error estimators.
method Reformulates calibration estimation as a regression problem with i.i.d. input pairs.
result Demonstrates the effectiveness of optimized calibration estimators on image classification tasks.
ManifoldMind uses adaptive-curvature probabilistic spheres for trustworthy recommendations in semantic hierarchies.
problem Sparse and abstract recommendation domains where users explore diverse conceptual paths.
method Adaptive-curvature probabilistic spheres, soft multi-hop inference, and curvature-aware semantic kernel.
result Superior NDCG, calibration, and diversity compared to baselines on public benchmarks.
Post-processing predictors reduces calibration errors for decision-making.
problem Predictors with low calibration error for machine learning may have high error for decision-making.
method Post-processing with ε distance to calibration adds noise to make predictions differentially private.
result Post-processing achieves O(√ε) ECE and CDL, asymptotically optimal.
A framework for analyzing regularizers to ensure trustworthy theory-driven model estimation.
problem Uncertain choice of regularizers can compromise the interpretability of deep grey-box models.
method Adapting neural net architecture and training objective to analyze regularizer behavior empirically.
result Empirical analysis of regularizers helps in making a justified choice for trustworthy theory-driven model estimation.
VisRuler simplifies decision extraction from bagged and boosted trees.
problem Complexity and lack of interpretability in ensemble models.
method Visual analytics tool for selecting robust models, important features, and essential decisions.
result Users successfully extracted and explained decisions from ensemble models.
Fair ML systems can be safe ML systems by considering uncertainty.
problem Safety of data-driven decision systems is often neglected.
method Viewing ML systems as socio-technical, uncertainty-aware modeling.
result Fair models should be uncertainty-aware, e.g. through distributional regression.
Study detects and explains positional bias in financial LLMs.
problem Positional bias in financial decision-making using LLMs.
method Unified framework and benchmark for detecting and quantifying bias in Qwen2.5 models.
result Positional bias is pervasive, scale-sensitive, and resurfaces under nuanced prompt designs.
New research finds tree-based GAMs are most trustworthy and fair.
problem Variability in GAM algorithms leads to inconsistent models.
method Quantitative and qualitative analysis of various GAM algorithms.
result Tree-based GAMs are the most trustworthy and fair.
FST.ai 2.0 improves Taekwondo decision-making with AI, reducing review time and increasing trust.
problem Fair, transparent, and explainable decision-making in Taekwondo.
method Pose-based action recognition, epistemic uncertainty modeling, interactive dashboards.
result 85% reduction in decision review time, 93% referee trust in AI-assisted decisions.
Framework audits synthetic datasets for trustworthiness across various use cases.
problem Assessing the trustworthiness of synthetic datasets and models.
method Holistic auditing framework focusing on bias, fidelity, utility, robustness, and privacy.
result Introduces a trustworthiness index and model selection process for controllable trade-offs.
In the context of fake news, bias, and propaganda, we study two important but relatively under-explored problems: (i) trustworthiness estimation (on a 3-point scale) and (ii) political ideology detection (left/right bias on a 7-point scale) of entire news outlets, as opposed to evaluating individual articles. In partic…
The paper addresses decision making with partially calibrated forecasts, offering a robust approach.
problem Developing a decision-making strategy for forecasts that are only partially calibrated.
method A minimax approach to mapping predictions to actions, considering worst-case distributions.
result The minimax optimal decision rule is to trust predictions and act accordingly, even for partially calibrated forecasts.
Proposes a game-theoretic framework for ML trust regulation.
problem Lack of coordination between ML model builders and regulators.
method Formulates trustworthy ML as a multi-objective multi-agent optimization problem and introduces regulation games and ParetoPlay.
result Enables efficient enforcement of ML model specifications without discouraging participation.
Survey of technologies for trustworthy machine learning systems.
problem Building machine learning systems that are fair, explainable, auditable, and secure.
method Survey of technologies across data and model stages of machine learning.
result Four categories of system properties (fairness, explainability, auditability, safety & security) are essential for trustworthy systems.
Most machine learning classifiers give predictions for new examples accurately, yet without indicating how trustworthy predictions are. In the medical domain, this hampers their integration in decision support systems, which could be useful in the clinical practice. We use a supervised learning approach that combines E…
Paper monitors DNN accuracy to enhance trustworthiness.
problem Varying DNN accuracy in practice and lack of ground truth labels.
method Post-hoc accuracy monitor model using Monte-Carlo dropout ensemble.
result Accuracy monitor provides close-to-true accuracy estimation.
Privacy and transparency are two key foundations of trustworthy machine learning. Model explanations offer insights into a model's decisions on input data, whereas privacy is primarily concerned with protecting information about the training data. We analyze connections between model explanations and the leakage of sen…
Paper defines ε-Safe Decision Regions for exponential family distributions and approximates them for unbalanced data.
problem Need probabilistic guarantees for reliable predictions in machine learning.
method Formalizes ε-Safe Decision Regions, proves their form for exponential family distributions, and develops Multi Cost SVM for unbalanced data.
result Formal definition and analytical determination of ε-Safe Decision Regions for exponential family distributions.
While social networks can provide an ideal platform for up-to-date information from individuals across the world, it has also proved to be a place where rumours fester and accidental or deliberate misinformation often emerges. In this article, we aim to support the task of making sense from social media data, and speci…
Online health communities are a valuable source of information for patients and physicians. However, such user-generated resources are often plagued by inaccuracies and misinformation. In this work we propose a method for automatically establishing the credibility of user-generated medical statements and the trustworth…
Statisticians contribute to LLMs for better trust and transparency.
problem Emerging statistical challenges in LLMs.
method Exploring statistical contributions to LLMs.
result Statisticians can enhance LLMs' trustworthiness and transparency.
Develops a new approach for algorithmic recourse in AI systems.
problem Tackles the problem of providing recommendations for reversing negative AI decisions.
method Introduces a causal framework that models recourse as a process over pre- and post-intervention outcomes, allowing for partial stability and resampling of latent variables.
result Demonstrates the value of the proposed methods on real and semi-synthetic datasets.