New method to understand bias in word embeddings.
problem Understanding and mitigating bias in word embeddings.
method Developed a technique to trace bias origins back to training documents.
result Accurate approximations of bias reduction can be made.
Avoid explaining black box models; use interpretable ones instead.
problem High-stakes decisions made by black box models cause societal harm.
method Design inherently interpretable models instead of trying to explain black box models.
result Inherently interpretable models are a better approach for high-stakes decisions.
LLM sandbox and persona dynamics create unethical reality gaps that shift risk to users.
problem Ethical issues arise from LLMs generating reality gaps that shift risk to uninformed users.
method Analyzes the ethical implications of LLM sandbox and persona dynamics, comparing them to financial regulation and compliance.
result Active generation of reality gaps is unethical as it shifts epistemic risk to users.
FairLangProc simplifies fairness in NLP models for Python users.
problem Addressing bias in NLP models for decision-making contexts.
method Develops a Python package for implementing fairness metrics and algorithms.
result Promotes the use of bias mitigation techniques in NLP.
Proposes a framework to create fair IDRs by enforcing demographic parity constraints.
problem Discrimination in IDRs trained on biased data.
method Incorporates DP and CDP constraints into IDR estimation.
result Theoretically optimal IDRs can be efficiently obtained through perturbations.
Proposes a new method to measure and avoid harm in machine learning decisions.
problem Measuring and avoiding harm in machine learning algorithms.
method Formal definition of harm and benefit using causal models, counterfactual objective functions.
result Demonstrates that standard machine learning methods can lead to harmful policies under distributional shifts.
Contrastive learning harms minority group representations, affecting downstream tasks.
problem Representation harm in contrastive learning, especially affecting minority groups.
method Causal mediation analysis and stochastic block model explanation.
result Representation harm in contrastive learning is partly responsible for allocation harm in downstream tasks.
The paper formalizes stereotyping in representation and proposes mitigation strategies.
problem Stereotyping in representation and its impact on allocation.
method Formalization of stereotyping, machine learning pipeline analysis, and mitigation strategies.
result Demonstrated effectiveness of mitigation strategies on synthetic datasets.
New framework controls statistical dispersion for high-stakes applications.
problem Understanding and controlling the dispersion of loss distributions in high-stakes applications.
method Simple yet flexible framework for distribution-free control of statistical dispersion measures.
result Proposed methods control statistical dispersion measures with societal implications.
PCL framework optimizes climate risk management across three clusters.
problem Comprehensive risk management in response to climate change impacts.
method Optimization of preemptive adaptation, contingent arrangements, and loss acceptance.
result Balanced portfolio of actions across three clusters optimized for long-term aggregate outlay.
Aims to create safe reinforcement learning policies by considering individual harm.
problem Optimal policies for a population may harm certain individuals.
method Formalizes individual harm, proposes a two-stage procedure, and establishes finite-sample properties.
result Learned policies maximize expected return while minimizing harm.
Researchers classify harmful structures on unimodular Lie groups.
problem Characterizing harmful structures on Lie groups.
method Analyzing left-invariant structures and using Clifford multiplication.
result Classification of harmful structures on unimodular Lie groups of dimension ≤ 4.
The paper outlines a framework to identify sources of harm in ML.
problem Understanding and mitigating harm in machine learning.
method Identifying seven sources of harm in ML life cycle stages.
result A framework to identify and mitigate harm in ML.
New fair regression method improves fairness in chronic kidney disease classification.
problem Mitigating societal bias in health care for multiple groups.
method Penalized fair regression framework for multiple groups, with penalties for true positive rate disparity.
result Achieves fairness-accuracy frontier beyond existing methods in simulations and real-world data.
Prediction models can harm patients even when accurate, leading to self-fulfilling prophecies.
problem Prediction models can lead to harmful decisions that worsen patient outcomes.
method Formal characterization of harmful prediction models and analysis of their impact.
result Well-calibrated models are ineffective for decision-making as they do not change the data distribution.
Optimizes fairness without sacrificing primary objectives.
problem Achieving fairness in optimization without reducing solution quality.
method Parametrized objective function to generate a set of optimal solutions, then optimize fairness using secondary criteria.
result Optimal solutions can be found that balance fairness and primary objectives.
New method stops experiments early for harm in diverse groups.
problem Early stopping of experiments for harmful treatment effects in diverse populations.
method Causal machine learning approach (CLASH) for early stopping.
result CLASH effectively stops experiments early for harmful treatment effects in diverse groups.
Study fair healthcare predictions without harming patients.
problem Balancing fairness and avoiding unnecessary harm in healthcare predictions.
method Formalizes Pareto-optimal approach to minimize risk disparity without causing harm, dynamically re-balancing subgroup risks.
result Demonstrates a method to train neural networks achieving fair predictions without unnecessary harm.
A new algorithm for fair decision-making in bandit problems with biased feedback.
problem Fair allocation of resources across sensitive groups in bandit problems with biased feedback.
method Proposes a novel algorithm that learns a societal bias term to mitigate unfairness in multi-armed bandit problems.
result The proposed algorithm achieves a theoretical bound on regret and demonstrates fairness in synthetic and real-world data.
Theorem. Let M be a compact, connected, oriented smooth Riemannian n-manifold with non-empty boundary. Then the cohomology of the complex (Harm*(M),d) of harmonic forms on M is given by the direct sum H^p(Harm*(M),d) = H^p(M;R) + H^(p-1)(M;R) for p=0,1,...,n. When M is a closed manifold, a form is harmonic if and only …
Framework generates precise synthetic populations for scalable modeling.
problem Generating accurate synthetic populations without personal data.
method Constraint-programming framework encoding aggregated statistics and structural relations.
result Exact control of demographic profiles without requiring microdata.
New method estimates harmful instances in GANs for better model performance.
problem Estimating harmful instances in GANs for improved model performance.
method Uses Jacobian of generator's loss to trace harmfulness of instances.
result Correctly inferred changes in GAN evaluation metrics and improved model performance.
Study proposes an alternative method to measure societal biases using smoothed co-occurrence relations.
problem Measuring societal biases using word embeddings can introduce irrelevant concepts.
method Proposes an alternative approach using smoothed first-order co-occurrence relations.
result First-order approach shows higher correlations with actual gender bias statistics.
When society maintains a competitive system to promote an abstract goal, competition by necessity relies on imperfect proxy measures. For instance profit is used to measure value to consumers, patient volumes to measure hospital performance, or the Journal Impact Factor to measure scientific value. Here we note that \t…
Study shows harmful overfitting in Sobolev spaces even as training data grows.
problem Harmful overfitting in Sobolev spaces under noisy conditions.
method Geometric argument using Sobolev inequalities.
result Approximately norm-minimizing interpolators exhibit harmful overfitting.
New framework shows algorithmic recourse can be harmful.
problem Risks of providing algorithmic recourse in binary classification.
method Abstract learning-theoretic framework comparing risks with and without recourse.
result Providing recourse can be harmful, increasing class uncertainty and mistakes.
Introduces data ethics for mathematicians, covering background, open data, and privacy.
problem Ensuring ethical use of data in mathematical research and education.
method Overview of data ethics concepts, societal context, and resources.
result Highlights the importance of ethical considerations in data use.
Improves GAN performance by identifying and removing harmful training instances.
problem Challenges in applying previous instance removal methods to GANs.
method Proposes influence estimation methods using Jacobian of generator's gradient and instance evaluation scheme based on GAN evaluation metrics.
result Removing harmful instances significantly improves GAN performance.
Proposes a new fairness definition based on equity for machine learning classification.
problem Machine learning systems can perpetuate societal biases.
method Formalizes a new fairness definition based on equity, operationalizes it for classification, and evaluates its effectiveness.
result Demonstrates the effectiveness of the new fairness definition for equitable classification.
Bayesian approach quantifies uncertainty in LLM evaluations.
problem Statistical uncertainty in evaluating LLM behavior.
method Bayesian evaluation of LLM behavior using probabilistic text generation strategies.
result Bayesian approach provides useful uncertainty quantification about LLM behavior.
PEF identifies the best subgroup performance balance for fairness.
problem Fairness constraints can degrade performance in skewed datasets.
method PEF identifies the closest operating point on the Pareto curve of subgroup performances.
result PEF achieves Pareto levels in accuracy for all subgroups.
The study finds that memorization is necessary or harmful depending on the prior distribution and noise level.
problem The impact of memorization on generalization in overparameterized models.
method An overparameterized linear model with general priors in a Bayesian setup.
result Explicit conditions for optimal generalization based on the prior distribution and noise level.
Improves fairness in machine learning by adding underrepresented group data.
problem Machine learning biases across subgroups due to under-representation or societal biases.
method Data augmentation via pairwise mixup across subgroups to balance subpopulations.
result Achieves fair outcomes with robust if not improved accuracy.
New framework assesses LLM security risks in BFSI.
problem Lack of domain-specific security evaluation for LLMs in BFSI.
method Risk-aware evaluation framework combining taxonomy, automated red-teaming, and ensemble judging.
result Higher decoding stochasticity and adaptive interaction lead to more severe disclosures.
New fairness criteria for algorithmic recourse actions that consider causal relationships.
problem Fairness of recourse actions in algorithmic classification.
method Proposes two new fairness criteria at group and individual levels, explicitly accounting for causal relationships.
result Fairness of recourse is complementary to fairness of prediction, and can be enforced by altering the classifier.
Proposes CSRN for better news recommendation by integrating RNN and UserCF.
problem Lack of societal influence in news recommendation.
method Integrates RNN-based sequential recommendation and UserCF, using a directed co-reading network.
result Significantly outperforms state-of-the-art approaches in news recommendation.
Study characterizes harmful low-fidelity data sources for surrogate models.
problem Identifying which low-fidelity data sources to use in constructing surrogate models.
method Employed benchmark filtering techniques to assess harmful sources using limited data.
result Provided guidelines for using low-fidelity sources in an industrial setting.
New bounds show multicalibration error is close to prediction error.
problem Addressing fairness in machine learning systems.
method Sample complexity bounds for uniform convergence of multicalibration error.
result Uniform convergence guarantees for multicalibration error, independent of prediction error.
Introduces MPR to measure and optimize representation across intersectional groups in retrieval.
problem Harmful stereotypes, cultural erasure, and social disparities in image search and retrieval.
method Develops MPR metric, practical estimation methods, theoretical guarantees, and optimization algorithms.
result Optimizing MPR yields more proportional representation across multiple intersectional groups, often with minimal retrieval accuracy compromise.
Study finds telemetric data not effective for predicting truck accident risk.
problem Estimating the risk of truck accidents using telemetric data.
method Used machine learning approaches: Random Forests and Convolutional Neural Networks.
result Neither approach successfully predicted truck accident risk.
New metric predicts neural network reliability under novel conditions.
problem Verifying neural networks' safety in novel scenarios.
method ML Dependability metric, Task Undependability, Harmful Undependability.
result Accurately predicts reliability under novel conditions.
Diffusion LLMs can efficiently generate harmful prompts for adversarial testing.
problem Generating harmful prompts for adversarial testing is resource-intensive and costly.
method Transformed adversarial prompt optimization into an efficient inference task using pretrained Diffusion LLMs.
result Only a few conditional samples are required to generate harmful prompts with high reward.
Detects harmful distribution shifts in deployed models without false alarms.
problem Detecting harmful distribution shifts in deployed models without false alarms.
method Sequential tools for testing if the difference between source and target distributions leads to a significant increase in a risk function.
result Demonstrated the efficacy of the proposed framework through extensive empirical studies.
New method detects long-term structures with internal dynamics in time series data.
problem Identifying patterns across time in data growth.
method Adaptive identification of majority overlaps between groups at different time points.
result Detection of persistent structural elements with internal dynamics.
Combining ensembles and data augmentation harms model calibration.
problem Improving model calibration and robustness with ensembles and data augmentation leads to a trade-off.
method Combining ensemble averaging and data augmentation techniques.
result Combining ensembles and data augmentation can harm model calibration.
Notions of "fair classification" that have arisen in computer science generally revolve around equalizing certain statistics across protected groups. This approach has been criticized as ignoring societal issues, including how errors can hurt certain groups disproportionately. We pose a modification of one of the fairn…
Selective planning with imperfect models reduces harmful effects of model inadequacy.
problem Harmful effects of using an imperfect model in reinforcement learning.
method Selective planning with heteroscedastic regression to estimate predictive uncertainty from model inadequacy.
result Effective selective planning requires considering both parameter uncertainty and model inadequacy.
Demonstrates ABCE's fairness analysis in complex systems.
problem Complex stochastic systems and subjective value criteria.
method Agent-based computational economics.
result Shows ABCE's capability for fairness analysis.