Michael Hind

David Piorkowski, Michael Hind, John Richards · ibm-research

Although AI systems are increasingly being leveraged to provide value to organizations, individuals, and society, significant attendant risks have been identified and have manifested. These risks have led to proposed regulations, litigation, and general societal concerns. As with any promising technology, organizations want to benefit from the positive capabilities of AI technology while reducing the risks. The best way to reduce risks is to implement comprehensive AI lifecycle governance where policies and procedures are described and enforced during the design, development, deployment, and monitoring of an AI system. Although support for comprehensive governance is beginning to emerge, organizations often need to identify the risks of deploying an already-built model without knowledge of how it was constructed or access to its original developers. Such an assessment will quantitatively assess the risks of an existing model in a manner analogous to how a home inspector might assess the risks of an already-built home or a physician might assess overall patient health based on a battery of tests. Several AI risks can be quantified using metrics from the technical community. However, there are numerous issues in deciding how these metrics can be leveraged to create a quantitative AI risk assessment. This paper explores these issues, focusing on the opportunities, challenges, and potential impacts of such an approach, and discussing how it might influence AI regulations.

Michael Hind, Basel Shbita, Bo Wu et al.

Textual Large Language Models (LLMs) provide a simple and familiar interface: a string of text is used for both input and output. However, the information conveyed to an LLM often has a richer structure and semantics, which is not conveyed in a string. For example, most prompts contain both instructions ("Summarize this paper into a paragraph") and data (the paper to summarize), but these are usually not distinguished when passed to the model. This can lead to model confusion and security risks, such as prompt injection attacks. This work addresses this shortcoming by introducing an LLM-native mark-up language, LLMON (LLM Object Notation, pronounced "Lemon"), that enables the structure and semantic metadata of the text to be communicated in a natural way to an LLM. This information can then be used during model training, model prompting, and inference implementation, leading to improvements in model accuracy, safety, and security. This is analogous to how programming language types can be used for many purposes, such as static checking, code generation, dynamic checking, and IDE highlighting. We discuss the general design requirements of an LLM-native markup language, introduce the LLMON markup language and show how it meets these design requirements, describe how the information contained in a LLMON artifact can benefit model training and inference implementation, and provide some preliminary empirical evidence of its value for both of these use cases. We also discuss broader issues and research opportunities that are enabled with an LLM-native approach.

Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia et al. · ibm-research

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). These models offer comprehensive coverage across multiple risk dimensions, including social bias, profanity, violence, sexual content, unethical behavior, jailbreaking, and hallucination-related risks such as context relevance, groundedness, and answer relevance for retrieval-augmented generation (RAG). Trained on a unique dataset combining human annotations from diverse sources and synthetic data, Granite Guardian models address risks typically overlooked by traditional risk detection models, such as jailbreaks and RAG-specific issues. With AUC scores of 0.871 and 0.854 on harmful content and RAG-hallucination-related benchmarks respectively, Granite Guardian is the most generalizable and competitive model available in the space. Released as open-source, Granite Guardian aims to promote responsible AI development across the community. https://github.com/ibm-granite/granite-guardian

Anna Sokol, Elizabeth Daly, Michael Hind et al.

Large language models (LLMs) are powerful tools capable of handling diverse tasks. Comparing and selecting appropriate LLMs for specific tasks requires systematic evaluation methods, as models exhibit varying capabilities across different domains. However, finding suitable benchmarks is difficult given the many available options. This complexity not only increases the risk of benchmark misuse and misinterpretation but also demands substantial effort from LLM users, seeking the most suitable benchmarks for their specific needs. To address these issues, we introduce \texttt{BenchmarkCards}, an intuitive and validated documentation framework that standardizes critical benchmark attributes such as objectives, methodologies, data sources, and limitations. Through user studies involving benchmark creators and users, we show that \texttt{BenchmarkCards} can simplify benchmark selection and enhance transparency, facilitating informed decision-making in evaluating LLMs. Data & Code: https://github.com/SokolAnn/BenchmarkCards

Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen et al.

As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, have different explanation needs. To address these needs, in 2019, we created AI Explainability 360 (Arya et al. 2020), an open source software toolkit featuring ten diverse and state-of-the-art explainability methods and two evaluation metrics. This paper examines the impact of the toolkit with several case studies, statistics, and community feedback. The different ways in which users have experienced AI Explainability 360 have resulted in multiple types of impact and improvements in multiple metrics, highlighted by the adoption of the toolkit by the independent LF AI & Data Foundation. The paper also describes the flexible design of the toolkit, examples of its use, and the significant educational material and documentation available to its users.

Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen et al.

As artificial intelligence and machine learning algorithms make further inroads into society, calls are increasing from multiple stakeholders for these algorithms to explain their outputs. At the same time, these stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, present different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360 (http://aix360.mybluemix.net/), an open-source software toolkit featuring eight diverse and state-of-the-art explainability methods and two evaluation metrics. 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. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. We also discuss enhancements to bring research innovations closer to consumers of explanations, ranging from simplified, more accessible versions of algorithms, to tutorials and an interactive web demo to introduce AI explainability to different audiences and application domains. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed.

Rachel K. E. Bellamy, Kuntal Dey, Michael Hind et al.

Fairness is an increasingly important concern as machine learning models are used to support decision making in high-stakes applications such as mortgage lending, hiring, and prison sentencing. This paper introduces a new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license {https://github.com/ibm/aif360). The main objectives of this toolkit are to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms. The package includes a comprehensive set of fairness metrics for datasets and models, explanations for these metrics, and algorithms to mitigate bias in datasets and models. It also includes an interactive Web experience (https://aif360.mybluemix.net) that provides a gentle introduction to the concepts and capabilities for line-of-business users, as well as extensive documentation, usage guidance, and industry-specific tutorials to enable data scientists and practitioners to incorporate the most appropriate tool for their problem into their work products. The architecture of the package has been engineered to conform to a standard paradigm used in data science, thereby further improving usability for practitioners. 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. A built-in testing infrastructure maintains code quality.

Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor et al. · ibm-research

Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations. Due to several limiting factors surrounding LLMs (training cost, API access, data availability, etc.), it may not always be feasible to impose direct safety constraints on a deployed model. Therefore, an efficient and reliable alternative is required. To this end, we present our ongoing efforts to create and deploy a library of detectors: compact and easy-to-build classification models that provide labels for various harms. In addition to the detectors themselves, we discuss a wide range of uses for these detector models - from acting as guardrails to enabling effective AI governance. We also deep dive into inherent challenges in their development and discuss future work aimed at making the detectors more reliable and broadening their scope.

Erik Miehling, Karthikeyan Natesan Ramamurthy, Kush R. Varshney et al.

The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current development of agentic AI requires a more holistic, systems-theoretic perspective in order to fully understand their capabilities and mitigate any emergent risks. The primary motivation for our position is that AI development is currently overly focused on individual model capabilities, often ignoring broader emergent behavior, leading to a significant underestimation in the true capabilities and associated risks of agentic AI. We describe some fundamental mechanisms by which advanced capabilities can emerge from (comparably simpler) agents simply due to their interaction with the environment and other agents. Informed by an extensive amount of existing literature from various fields, we outline mechanisms for enhanced agent cognition, emergent causal reasoning ability, and metacognitive awareness. We conclude by presenting some key open challenges and guidance for the development of agentic AI. We emphasize that a systems-level perspective is essential for better understanding, and purposefully shaping, agentic AI systems.

Elizabeth M. Daly, Sean Rooney, Seshu Tirupathi et al.

Evaluating the safety of AI Systems is a pressing concern for organizations deploying them. In addition to the societal damage done by the lack of fairness of those systems, deployers are concerned about the legal repercussions and the reputational damage incurred by the use of models that are unsafe. Safety covers both what a model does; e.g., can it be used to reveal personal information from its training set, and how a model was built; e.g., was it only trained on licensed data sets. Determining the safety of an AI system requires gathering information from a wide set of heterogeneous sources including safety benchmarks and technical documentation for the set of models used in that system. In addition, responsible use is encouraged through mechanisms that advise and help the user to take mitigating actions where safety risks are detected. We present Usage Governance Advisor which creates semi-structured governance information, identifies and prioritizes risks according to the intended use case, recommends appropriate benchmarks and risk assessments and importantly proposes mitigation strategies and actions.

David Piorkowski, John Richards, Michael Hind

In reaction to growing concerns about the potential harms of artificial intelligence (AI), societies have begun to demand more transparency about how AI models and systems are created and used. To address these concerns, several efforts have proposed documentation templates containing questions to be answered by model developers. These templates provide a useful starting point, but no single template can cover the needs of diverse documentation consumers. It is possible in principle, however, to create a repeatable methodology to generate truly useful documentation. Richards et al. [25] proposed such a methodology for identifying specific documentation needs and creating templates to address those needs. Although this is a promising proposal, it has not been evaluated. This paper presents the first evaluation of this user-centered methodology in practice, reporting on the experiences of a team in the domain of AI for healthcare that adopted it to increase transparency for several AI models. The methodology was found to be usable by developers not trained in user-centered techniques, guiding them to creating a documentation template that addressed the specific needs of their consumers while still being reusable across different models and use cases. Analysis of the benefits and costs of this methodology are reviewed and suggestions for further improvement in both the methodology and supporting tools are summarized.

Tim Draws, Zoltán Szlávik, Benjamin Timmermans et al.

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. However, recent research has demonstrated that the machine learning algorithms that often underlie such technology can act unfairly towards specific groups (e.g., by making more favorable predictions for men than for women). An undesired disparate impact resulting from this kind of algorithmic unfairness could diminish consumer trust and thereby undermine the purpose of the system. We studied this effect by conducting a between-subjects user study investigating how (gender-related) disparate impact affected consumer trust in an app designed to improve consumers' financial decision-making. Our results show that disparate impact decreased consumers' trust in the system and made them less likely to use it. Moreover, we find that trust was affected to the same degree across consumer groups (i.e., advantaged and disadvantaged users) despite both of these consumer groups recognizing their respective levels of personal benefit. Our findings highlight the importance of fairness in consumer-oriented artificial intelligence systems.

John Richards, David Piorkowski, Michael Hind et al.

As AI models and services are used in a growing number of highstakes areas, a consensus is forming around the need for a clearer record of how these models and services are developed to increase trust. Several proposals for higher quality and more consistent AI documentation have emerged to address ethical and legal concerns and general social impacts of such systems. However, there is little published work on how to create this documentation. This is the first work to describe a methodology for creating the form of AI documentation we call FactSheets. We have used this methodology to create useful FactSheets for nearly two dozen models. This paper describes this methodology and shares the insights we have gathered. Within each step of the methodology, we describe the issues to consider and the questions to explore with the relevant people in an organization who will be creating and consuming the AI facts in a FactSheet. This methodology will accelerate the broader adoption of transparent AI documentation.

Stacy Hobson, Michael Hind, Aleksandra Mojsilovic et al.

The global outbreak of COVID-19 has led to focus on efforts to manage and mitigate the continued spread of the disease. One of these efforts include the use of contact tracing to identify people who are at-risk of developing the disease through exposure to an infected person. Historically, contact tracing has been primarily manual but given the exponential spread of the virus that causes COVID-19, there has been significant interest in the development and use of digital contact tracing solutions to supplement the work of human contact tracers. The collection and use of sensitive personal details by these applications has led to a number of concerns by the stakeholder groups with a vested interest in these solutions. We explore digital contact tracing solutions in detail and propose the use of a transparent reporting mechanism, FactSheets, to provide transparency of and support trust in these applications. We also provide an example FactSheet template with questions that are specific to the contact tracing application domain.

Michael Hind, Dennis Wei, Yunfeng Zhang

Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers. This paper builds upon an alternative consumer-driven approach called TED that asks for explanations to be provided in training data, along with target labels. Using semi-synthetic data from credit approval and employee retention applications, experiments are conducted to investigate some practical considerations with TED, including its performance with different classification algorithms, varying numbers of explanations, and variability in explanations. A new algorithm is proposed to handle the case where some training examples do not have explanations. Our results show that TED is robust to increasing numbers of explanations, noisy explanations, and large fractions of missing explanations, thus making advances toward its practical deployment.

Michael Hind, Stephanie Houde, Jacquelyn Martino et al.

AI models and services are used in a growing number of highstakes areas, resulting in a need for increased transparency. Consistent with this, several proposals for higher quality and more consistent documentation of AI data, models, and systems have emerged. Little is known, however, about the needs of those who would produce or consume these new forms of documentation. Through semi-structured developer interviews, and two document creation exercises, we have assembled a clearer picture of these needs and the various challenges faced in creating accurate and useful AI documentation. Based on the observations from this work, supplemented by feedback received during multiple design explorations and stakeholder conversations, we make recommendations for easing the collection and flexible presentation of AI facts to promote transparency.

Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy et al.

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. Recently, a new framework for providing explanations, called TED, has been proposed to provide meaningful explanations for predictions. This framework augments training data to include explanations elicited from domain users, in addition to features and labels. This approach ensures that explanations for predictions are tailored to the complexity expectations and domain knowledge of the consumer. In this paper, we build on this foundational work, by exploring more sophisticated instantiations of the TED framework and empirically evaluate their effectiveness in two diverse domains, chemical odor and skin cancer prediction. Results demonstrate that meaningful explanations can be reliably taught to machine learning algorithms, and in some cases, improving modeling accuracy.

Michael Hind, Dennis Wei, Murray Campbell et al.

Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation, there is a growing demand for such systems to provide explanations for their decisions. Conventional approaches to this problem attempt to expose or discover the inner workings of a machine learning model with the hope that the resulting explanations will be meaningful to the consumer. In contrast, this paper suggests a new approach to this problem. It introduces a simple, practical framework, called Teaching Explanations for Decisions (TED), that provides meaningful explanations that match the mental model of the consumer. We illustrate the generality and effectiveness of this approach with two different examples, resulting in highly accurate explanations with no loss of prediction accuracy for these two examples.

Ravi Kiran Raman, Roman Vaculin, Michael Hind et al.

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. For instance, the OpenMalaria framework is a computationally-intensive simulation used by various non-governmental and governmental agencies to understand malarial disease spread and effectiveness of intervention strategies, and subsequently design healthcare policies. Given that such shared results form the basis of inferences drawn, technological solutions designed, and day-to-day policies drafted, it is essential that the computations are validated and trusted. In particular, in a multi-agent environment involving several independent computing agents, a notion of trust in results generated by peers is critical in facilitating transparency, accountability, and collaboration. Using a novel combination of distributed validation of atomic computation blocks and a blockchain-based immutable audits mechanism, this work proposes a universal framework for distributed trust in computations. In particular we address the scalaibility problem by reducing the storage and communication costs using a lossy compression scheme. This framework guarantees not only verifiability of final results, but also the validity of local computations, and its cost-benefit tradeoffs are studied using a synthetic example of training a neural network.

Matthew Arnold, Rachel K. E. Bellamy, Michael Hind et al.

Accuracy is an important concern for suppliers of artificial intelligence (AI) services, but considerations beyond accuracy, such as safety (which includes fairness and explainability), security, and provenance, are also critical elements to engender consumers' trust in a service. Many industries use transparent, standardized, but often not legally required documents called supplier's declarations of conformity (SDoCs) to describe the lineage of a product along with the safety and performance testing it has undergone. SDoCs may be considered multi-dimensional fact sheets that capture and quantify various aspects of the product and its development to make it worthy of consumers' trust. Inspired by this practice, we propose FactSheets to help increase trust in AI services. We envision such documents to contain purpose, performance, safety, security, and provenance information to be completed by AI service providers for examination by consumers. We suggest a comprehensive set of declaration items tailored to AI and provide examples for two fictitious AI services in the appendix of the paper.

Noel C. F. Codella, Chung-Ching Lin, Allan Halpern et al.

Automated dermoscopic image analysis has witnessed rapid growth in diagnostic performance. Yet adoption faces resistance, in part, because no evidence is provided to support decisions. In this work, an approach for evidence-based classification is presented. A feature embedding is learned with CNNs, triplet-loss, and global average pooling, and used to classify via kNN search. Evidence is provided as both the discovered neighbors, as well as localized image regions most relevant to measuring distance between query and neighbors. To ensure that results are relevant in terms of both label accuracy and human visual similarity for any skill level, a novel hierarchical triplet logic is implemented to jointly learn an embedding according to disease labels and non-expert similarity. Results are improved over baselines trained on disease labels alone, as well as standard multiclass loss. Quantitative relevance of results, according to non-expert similarity, as well as localized image regions, are also significantly improved.

Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy et al.

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. In this paper, we propose an approach to generate such explanations in which training data is augmented to include, in addition to features and labels, explanations elicited from domain users. A joint model is then learned to produce both labels and explanations from the input features. This simple idea ensures that explanations are tailored to the complexity expectations and domain knowledge of the consumer. Evaluation spans multiple modeling techniques on a game dataset, a (visual) aesthetics dataset, a chemical odor dataset and a Melanoma dataset showing that our approach is generalizable across domains and algorithms. Results demonstrate that meaningful explanations can be reliably taught to machine learning algorithms, and in some cases, also improve modeling accuracy.