Search Results for author:
Found 76 papers, 13 papers with code
An Annotated Reading of 'The Singer of Tales' in the LLM Era
We point out the the similarities and differences between oral composition and LLM generation, and comment on the implications to society and AI policy.
Scopes of Alignment
Much of the research focus on AI alignment seeks to align large language models and other foundation models to the context-less and generic values of helpfulness, harmlessness, and honesty.
Granite Guardian
We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM).
Hey GPT, Can You be More Racist? Analysis from Crowdsourced Attempts to Elicit Biased Content from Generative AI
The widespread adoption of large language models (LLMs) and generative AI (GenAI) tools across diverse applications has amplified the importance of addressing societal biases inherent within these technologies.
Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
As generative AI, particularly large language models (LLMs), become increasingly integrated into production applications, new attack surfaces and vulnerabilities emerge and put a focus on adversarial threats in natural language and multi-modal systems.
Value Alignment from Unstructured Text
Aligning large language models (LLMs) to value systems has emerged as a significant area of research within the fields of AI and NLP.
Contextual Moral Value Alignment Through Context-Based Aggregation
Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI.
A resource-constrained stochastic scheduling algorithm for homeless street outreach and gleaning edible food
We developed a common algorithmic solution addressing the problem of resource-constrained outreach encountered by social change organizations with different missions and operations: Breaking Ground -- an organization that helps individuals experiencing homelessness in New York transition to permanent housing and Leket -- the national food bank of Israel that rescues food from farms and elsewhere to feed the hungry.
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
Rethinking Machine Unlearning for Large Language Models
We explore machine unlearning (MU) in the domain of large language models (LLMs), referred to as LLM unlearning.
Empathy and the Right to Be an Exception: What LLMs Can and Cannot Do
We propose that the method of empathy has special significance for honoring the right to be an exception that is distinct from the value of predictive accuracy, at which LLMs excel.
Decolonial AI Alignment: Openness, Viśe\d{s}a-Dharma, and Including Excluded Knowledges
Prior work has explicated the coloniality of artificial intelligence (AI) development and deployment through mechanisms such as extractivism, automation, sociological essentialism, surveillance, and containment.
Keeping Up with the Language Models: Systematic Benchmark Extension for Bias Auditing
We demonstrate that the newly created dataset BBNLI-next is more challenging than BBNLI: on average, BBNLI-next reduces the accuracy of state-of-the-art NLI models from 95. 3%, as observed by BBNLI, to a strikingly low 57. 5%.
Towards Healthy AI: Large Language Models Need Therapists Too
By incorporating psychotherapy and reinforcement learning techniques, the framework enables AI chatbots to learn and adapt to human preferences and values in a safe and ethical way, contributing to the development of a more human-centric and responsible AI.
Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions
In this paper, focusing specifically on compositions of functions arising from the different pillars, we aim to reduce this gap, develop new insights for trustworthy ML, and answer questions such as the following.
Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
The dropping of training points is done in principle, but in practice does not require the model to be refit.
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
Interpretable and explainable machine learning has seen a recent surge of interest.
Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models
We also provide a novel group-theoretic definition for fairness in NLG.
Minimax AUC Fairness: Efficient Algorithm with Provable Convergence
We conduct numerical experiments on both synthetic and real-world datasets to validate the effectiveness of the minimax framework and the proposed optimization algorithm.
Differentially Private SGDA for Minimax Problems
We further provide its utility analysis in the nonconvex-strongly-concave setting which is the first-ever-known result in terms of the primal population risk.
CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions
We experiment on nonlinear synthetic functions and are able to accurately model as well as estimate feature attributions and even higher order terms in some cases, which is a testament to the representational power as well as interpretability of such architectures.
Human-Centered Explainable AI (XAI): From Algorithms to User Experiences
In this chapter, we begin with a high-level overview of the technical landscape of XAI algorithms, then selectively survey our own and other recent HCI works that take human-centered approaches to design, evaluate, and provide conceptual and methodological tools for XAI.
An Empirical Study of Accuracy, Fairness, Explainability, Distributional Robustness, and Adversarial Robustness
To ensure trust in AI models, it is becoming increasingly apparent that evaluation of models must be extended beyond traditional performance metrics, like accuracy, to other dimensions, such as fairness, explainability, adversarial robustness, and distribution shift.
AI Explainability 360: Impact and Design
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations.
Towards Interpreting Zoonotic Potential of Betacoronavirus Sequences With Attention
Current methods for viral discovery target evolutionarily conserved proteins that accurately identify virus families but remain unable to distinguish the zoonotic potential of newly discovered viruses.
Biomedical Interpretable Entity Representations
Pre-trained language models induce dense entity representations that offer strong performance on entity-centric NLP tasks, but such representations are not immediately interpretable.
Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI
In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models.
Disparate Impact Diminishes Consumer Trust Even for Advantaged Users
Systems aiming to aid consumers in their decision-making (e. g., by implementing persuasive techniques) are more likely to be effective when consumers trust them.
Decision Making
Fairness
Human-Computer Interaction
Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
In this survey, we provide a systematic framework of Socially Responsible AI Algorithms that aims to examine the subjects of AI indifference and the need for socially responsible AI algorithms, define the objectives, and introduce the means by which we may achieve these objectives.
Learning to Initialize Gradient Descent Using Gradient Descent
Non-convex optimization problems are challenging to solve; the success and computational expense of a gradient descent algorithm or variant depend heavily on the initialization strategy.
Empirical or Invariant Risk Minimization? A Sample Complexity Perspective
Recently, invariant risk minimization (IRM) was proposed as a promising solution to address out-of-distribution (OOD) generalization.
Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making
We, then, conduct a second user experiment which shows that our time allocation strategy with explanation can effectively de-anchor the human and improve collaborative performance when the AI model has low confidence and is incorrect.
Causal Feature Selection for Algorithmic Fairness
In this work, we consider fairness in the integration component of data management, aiming to identify features that improve prediction without adding any bias to the dataset.
Invariant Risk Minimization Games
The standard risk minimization paradigm of machine learning is brittle when operating in environments whose test distributions are different from the training distribution due to spurious correlations.
Joint Optimization of AI Fairness and Utility: A Human-Centered Approach
Today, AI is increasingly being used in many high-stakes decision-making applications in which fairness is an important concern.
Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies
More than 200 generic drugs approved by the U. S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer.
Preservation of Anomalous Subgroups On Machine Learning Transformed Data
Our evaluation confirmed that the approach was able to produce synthetic datasets that preserved a high level of subgroup differentiation as identified initially in the original dataset.
DADI: Dynamic Discovery of Fair Information with Adversarial Reinforcement Learning
We introduce a framework for dynamic adversarial discovery of information (DADI), motivated by a scenario where information (a feature set) is used by third parties with unknown objectives.
Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets
We find that the majority of the data in the the two datasets have ITA values between 34. 5{\deg} and 48{\deg}, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets.
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
Moreover, the same classifier yields the lack of a trade-off with respect to ideal distributions while yielding a trade-off when accuracy is measured with respect to the given (possibly biased) dataset.
A Kolmogorov Complexity Approach to Generalization in Deep Learning
Using this condition, we formulate an optimization problem to learn a more general classification function.
How Data Scientists Work Together With Domain Experts in Scientific Collaborations: To Find The Right Answer Or To Ask The Right Question?
Our findings suggest that besides the glitches in the collaboration readiness, technology readiness, and coupling of work dimensions, the tensions that exist in the common ground building process influence the collaboration outcomes, and then persist in the actual collaboration process.
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability.
Characterization of Overlap in Observational Studies
Overlap between treatment groups is required for non-parametric estimation of causal effects.
Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning
Using machine learning in high-stakes applications often requires predictions to be accompanied by explanations comprehensible to the domain user, who has ultimate responsibility for decisions and outcomes.
Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
The dearth of prescribing guidelines for physicians is one key driver of the current opioid epidemic in the United States.
Bias Mitigation Post-processing for Individual and Group Fairness
Whereas previous post-processing approaches for increasing the fairness of predictions of biased classifiers address only group fairness, we propose a method for increasing both individual and group fairness.
Understanding Unequal Gender Classification Accuracy from Face Images
Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender.
TED: Teaching AI to Explain its Decisions
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions.
SimplerVoice: A Key Message & Visual Description Generator System for Illiteracy
We introduce SimplerVoice: a key message and visual description generator system to help low-literate adults navigate the information-dense world with confidence, on their own.
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking.
Trusted Multi-Party Computation and Verifiable Simulations: A Scalable Blockchain Approach
Large-scale computational experiments, often running over weeks and over large datasets, are used extensively in fields such as epidemiology, meteorology, computational biology, and healthcare to understand phenomena, and design high-stakes policies affecting everyday health and economy.
FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformity
We envision such documents to contain purpose, performance, safety, security, and provenance information to be completed by AI service providers for examination by consumers.
Teaching machines to understand data science code by semantic enrichment of dataflow graphs
Your computer is continuously executing programs, but does it really understand them?
Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018)
This is the Proceedings of the 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), which was held in Stockholm, Sweden, July 14, 2018.
Why Interpretability in Machine Learning? An Answer Using Distributed Detection and Data Fusion Theory
Such arguments, however, fail to acknowledge that the overall decision-making system is composed of two entities: the learned model and a human who fuses together model outputs with his or her own information.
Teaching Meaningful Explanations
The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate responsibility for decisions and outcomes.
Topological Data Analysis of Decision Boundaries with Application to Model Selection
We propose the labeled \v{C}ech complex, the plain labeled Vietoris-Rips complex, and the locally scaled labeled Vietoris-Rips complex to perform persistent homology inference of decision boundaries in classification tasks.
Fairness GAN
In this paper, we introduce the Fairness GAN, an approach for generating a dataset that is plausibly similar to a given multimedia dataset, but is more fair with respect to protected attributes in allocative decision making.
Structure Learning from Time Series with False Discovery Control
Almost all existing Granger causal algorithms condition on a large number of variables (all but two variables) to test for effects between a pair of variables.
The Effect of Extremist Violence on Hateful Speech Online
In this paper, we focus on quantifying the impact of violent events on various types of hate speech, from offensive and derogatory to intimidation and explicit calls for violence.
Social and Information Networks Computers and Society
How an Electrical Engineer Became an Artificial Intelligence Researcher, a Multiphase Active Contours Analysis
This essay examines how what is considered to be artificial intelligence (AI) has changed over time and come to intersect with the expertise of the author.
Optimized Pre-Processing for Discrimination Prevention
Non-discrimination is a recognized objective in algorithmic decision making.
Neurology-as-a-Service for the Developing World
In this work, we present a cloud-based deep neural network approach to provide decision support for non-specialist physicians in EEG analysis and interpretation.
Distribution-Preserving k-Anonymity
Preserving the privacy of individuals by protecting their sensitive attributes is an important consideration during microdata release.
Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017)
This is the Proceedings of the 2017 ICML Workshop on Human Interpretability in Machine Learning (WHI 2017), which was held in Sydney, Australia, August 10, 2017.
Optimized Data Pre-Processing for Discrimination Prevention
Non-discrimination is a recognized objective in algorithmic decision making.
On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products
Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives.
Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016)
This is the Proceedings of the 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), which was held in New York, NY, June 23, 2016.
Proceedings of the 2016 ICML Workshop on #Data4Good: Machine Learning in Social Good Applications
This is the Proceedings of the ICML Workshop on #Data4Good: Machine Learning in Social Good Applications, which was held on June 24, 2016 in New York.
Interpretable Two-level Boolean Rule Learning for Classification
As a contribution to interpretable machine learning research, we develop a novel optimization framework for learning accurate and sparse two-level Boolean rules.
Understanding Innovation to Drive Sustainable Development
Innovation is among the key factors driving a country's economic and social growth.
Dynamic matrix factorization with social influence
Matrix factorization is a key component of collaborative filtering-based recommendation systems because it allows us to complete sparse user-by-item ratings matrices under a low-rank assumption that encodes the belief that similar users give similar ratings and that similar items garner similar ratings.
Engineering Safety in Machine Learning
Machine learning algorithms are increasingly influencing our decisions and interacting with us in all parts of our daily lives.
Interpretable Two-level Boolean Rule Learning for Classification
Experiments show that the two-level rules can yield noticeably better performance than one-level rules due to their dramatically larger modeling capacity, and the two algorithms based on the Hamming distance formulation are generally superior to the other two-level rule learning methods in our comparison.
A Big Data Approach to Computational Creativity
Computational creativity is an emerging branch of artificial intelligence that places computers in the center of the creative process.
