Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

Bhatt, Umang; Antorán, Javier; Zhang, Yunfeng; Liao, Q. Vera; Sattigeri, Prasanna; Fogliato, Riccardo; Melançon, Gabrielle Gauthier; Krishnan, Ranganath; Stanley, Jason; Tickoo, Omesh; Nachman, Lama; Chunara, Rumi; Srikumar, Madhulika; Weller, Adrian; Xiang, Alice

doi:10.1145/3461702.3462571

Cited by 146 publications

(101 citation statements)

References 104 publications

(95 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Concerning auditing, recent work underscores the importance of being able to analyze algorithmic outputs to detect and correct for the harm of unfair discrimination [4,110]. Transparency tends to be treated as a property of models, particularly with regard to whether a model is interpretable or explainable to relevant stakeholders [14,40,52]. 2 More recently, computational work has begun to take a more expansive view of transparency, applying it to other parts of the ML pipeline, such as problem formulation, data provenance, and model selection choices [50,50,81,121,122].…”

Section: Contemporary Interventions In Accountability and Data-driven...mentioning

confidence: 99%

See 1 more Smart Citation

Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning

Cooper,

Moss,

Laufer

et al. 2022

Preprint

View full text Add to dashboard Cite

In 1996, philosopher Helen Nissenbaum issued a clarion call concerning the erosion of accountability in society due to the ubiquitous delegation of consequential functions to computerized systems. Using the conceptual framing of moral blame, Nissenbaum described four types of barriers to accountability that computerization presented: 1) "many hands," the problem of attributing moral responsibility for outcomes caused by many moral actors; 2) "bugs," a way software developers might shrug off responsibility by suggesting software errors are unavoidable; 3) "computer as scapegoat," shifting blame to computer systems as if they were moral actors; and 4) "ownership without liability," a free pass to the tech industry to deny responsibility for the software they produce. We revisit these four barriers in relation to the recent ascendance of data-driven algorithmic systemstechnology often folded under the heading of machine learning (ML) or artificial intelligence (AI) -to uncover the new challenges for accountability that these systems present. We then look ahead to how one might construct and justify a moral, relational framework for holding responsible parties accountable, and argue that the FAccT community is uniquely well-positioned to develop such a framework to weaken the four barriers.

show abstract

Section: Contemporary Interventions In Accountability and Data-driven...mentioning

confidence: 99%

“…In short, satisfying mathematical guarantees can serve as a scapegoat because pointing to mathematical claims satisfied at the model-level can serve to obscure the need to account for harms that occur at the individual-decision level. 14 Non-determinism. Data-driven algorithmic systems that involve ML exhibit non-determinism.…”

Section: The Computer As Scapegoatmentioning

confidence: 99%

Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning

Cooper,

Moss,

Laufer

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…An emerging challenge with using NNs for anomaly detection is the quantification of uncertainty [20]. Uncertainty is a core component for promoting algorithmic transparency and hence, the advancement of trustworthy ML [22].…”

Section: Background and Related Workmentioning

confidence: 99%

Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection

Yong¹,

Brintrup²

2022

Preprint

View full text Add to dashboard Cite

Despite numerous studies of deep autoencoders (AEs) for unsupervised anomaly detection, AEs still lack a way to express uncertainty in their predictions, crucial for ensuring safe and trustworthy machine learning systems in high-stake applications. Therefore, in this work, the formulation of Bayesian autoencoders (BAEs) is adopted to quantify the total anomaly uncertainty, comprising epistemic and aleatoric uncertainties. To evaluate the quality of uncertainty, we consider the task of classifying anomalies with the additional option of rejecting predictions of high uncertainty. In addition, we use the accuracy-rejection curve and propose the weighted average accuracy as a performance metric. Our experiments demonstrate the effectiveness of the BAE and total anomaly uncertainty on a set of benchmark datasets and two real datasets for manufacturing: one for condition monitoring, the other for quality inspection.

show abstract

“…Depending on user needs, it may be more critical to provide transparent information about a model's capabilities, limitations (e.g. uncertainty [10]) or provenance [8]. Moreover, users may need additional information beyond algorithmic explanations to fill in gaps of understanding.…”

Section: Introductionmentioning

confidence: 99%

Investigating Explainability of Generative AI for Code through Scenario-based Design

Sun

Liao²,

Müller

et al. 2022

27th International Conference on Intelligent User Interfaces

Self Cite

107

View full text Add to dashboard Cite

What does it mean for a generative AI model to be explainable? The emergent discipline of explainable AI (XAI) has made great strides in helping people understand discriminative models. Less attention has been paid to generative models that produce artifacts, rather than decisions, as output. Meanwhile, generative AI (GenAI) technologies are maturing and being applied to application domains such as software engineering. Using scenario-based design and question-driven XAI design approaches, we explore users' explainability needs for GenAI in three software engineering use cases: natural language to code, code translation, and code autocompletion. We conducted 9 workshops with 43 software engineers in which real examples from state-of-the-art generative AI models were used to elicit users' explainability needs. Drawing from prior work, we also propose 4 types of XAI features for GenAI for code and gathered additional design ideas from participants. Our work explores explainability needs for GenAI for code and demonstrates how human-centered approaches can drive the technical development of XAI in novel domains. CCS CONCEPTS• Computing methodologies → Natural language generation; • Software and its engineering; • Human-centered computing → Human computer interaction (HCI); User studies;

show abstract

Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty

Cited by 146 publications

References 104 publications

Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning

Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning

Bayesian autoencoders with uncertainty quantification: Towards trustworthy anomaly detection

Investigating Explainability of Generative AI for Code through Scenario-based Design

Contact Info

Product

Resources

About