Emanuel Moss

Matthew Stewart, Yuke Zhang, Pete Warden et al.

Machine learning (ML) is becoming prevalent in embedded AI sensing systems. These "ML sensors" enable context-sensitive, real-time data collection and decision-making across diverse applications ranging from anomaly detection in industrial settings to wildlife tracking for conservation efforts. As such, there is a need to provide transparency in the operation of such ML-enabled sensing systems through comprehensive documentation. This is needed to enable their reproducibility, to address new compliance and auditing regimes mandated in regulation and industry-specific policy, and to verify and validate the responsible nature of their operation. To address this gap, we introduce the datasheet for ML sensors framework. We provide a comprehensive template, collaboratively developed in academia-industry partnerships, that captures the distinct attributes of ML sensors, including hardware specifications, ML model and dataset characteristics, end-to-end performance metrics, and environmental impacts. Our framework addresses the continuous streaming nature of sensor data, real-time processing requirements, and embeds benchmarking methodologies that reflect real-world deployment conditions, ensuring practical viability. Aligned with the FAIR principles (Findability, Accessibility, Interoperability, and Reusability), our approach enhances the transparency and reusability of ML sensor documentation across academic, industrial, and regulatory domains. To show the application of our approach, we present two datasheets: the first for an open-source ML sensor designed in-house and the second for a commercial ML sensor developed by industry collaborators, both performing computer vision-based person detection.

Emanuel Moss, Elizabeth Watkins, Christopher Persaud et al.

As generative AI technologies are pressed into service in workplace settings, current approaches to account for the contexts in which such technologies are used fall short of users' expectations and needs. This paper empirically demonstrates, through expert interviews, both how these tools fail to account for users' context and how users deploy concrete strategies address such failures. The paper analyzes how context is variously conceptualized by tool developers, users, and social scientists to identify specific pitfalls inherent in computational approaches to context. Multiple distinct contexts tend to collapse into one another or rot, degrading over time, reducing the utility of any efforts to account for context. The paper concludes with a provocation to shift from an indiscriminate collection of context-relevant data toward a more interactional set of practices to embed GenAI systems more appropriately into users' contexts of use.

Bertie Vidgen, Adarsh Agrawal, Ahmed M. Ahmed et al. · deepmind, oxford

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models. We introduce a principled approach to specifying and constructing the benchmark, which for v0.5 covers only a single use case (an adult chatting to a general-purpose assistant in English), and a limited set of personas (i.e., typical users, malicious users, and vulnerable users). We created a new taxonomy of 13 hazard categories, of which 7 have tests in the v0.5 benchmark. We plan to release version 1.0 of the AI Safety Benchmark by the end of 2024. The v1.0 benchmark will provide meaningful insights into the safety of AI systems. However, the v0.5 benchmark should not be used to assess the safety of AI systems. We have sought to fully document the limitations, flaws, and challenges of v0.5. This release of v0.5 of the AI Safety Benchmark includes (1) a principled approach to specifying and constructing the benchmark, which comprises use cases, types of systems under test (SUTs), language and context, personas, tests, and test items; (2) a taxonomy of 13 hazard categories with definitions and subcategories; (3) tests for seven of the hazard categories, each comprising a unique set of test items, i.e., prompts. There are 43,090 test items in total, which we created with templates; (4) a grading system for AI systems against the benchmark; (5) an openly available platform, and downloadable tool, called ModelBench that can be used to evaluate the safety of AI systems on the benchmark; (6) an example evaluation report which benchmarks the performance of over a dozen openly available chat-tuned language models; (7) a test specification for the benchmark.

Ramesh Manuvinakurike, Emanuel Moss, Elizabeth Anne Watkins et al.

Agentic pipelines present novel challenges and opportunities for human-centered explainability. The HCXAI community is still grappling with how best to make the inner workings of LLMs transparent in actionable ways. Agentic pipelines consist of multiple LLMs working in cooperation with minimal human control. In this research paper, we present early findings from an agentic pipeline implementation of a perceptive task guidance system. Through quantitative and qualitative analysis, we analyze how Chain-of-Thought (CoT) reasoning, a common vehicle for explainability in LLMs, operates within agentic pipelines. We demonstrate that CoT reasoning alone does not lead to better outputs, nor does it offer explainability, as it tends to produce explanations without explainability, in that they do not improve the ability of end users to better understand systems or achieve their goals.

Elizabeth Anne Watkins, Emanuel Moss, Ramesh Manuvinakurike et al.

In this short paper we address issues related to building multimodal AI systems for human performance support in manufacturing domains. We make two contributions: we first identify challenges of participatory design and training of such systems, and secondly, to address such challenges, we propose the ACE paradigm: "Action and Control via Explanations". Specifically, we suggest that LLMs can be used to produce explanations in the form of human interpretable "semantic frames", which in turn enable end users to provide data the AI system needs to align its multimodal models and representations, including computer vision, automatic speech recognition, and document inputs. ACE, by using LLMs to "explain" using semantic frames, will help the human and the AI system to collaborate, together building a more accurate model of humans activities and behaviors, and ultimately more accurate predictive outputs for better task support, and better outcomes for human users performing manual tasks.

Emanuel Moss, Elizabeth Watkins, Christopher Persaud et al.

Generative AI tools have become more prevalent in engineering workflows, particularly through chatbots and code assistants. As the perceived accuracy of these tools improves, questions arise about whether and how those who work in high-precision domains might maintain vigilance for errors, and what other aspects of using such tools might trouble their work. This paper analyzes interviews with hardware and software engineers, and their collaborators, who work in integrated circuit design to identify the role accuracy plays in their use of generative AI tools and what other forms of trouble they face in using such tools. The paper inventories these forms of trouble, which are then mapped to elements of generative AI systems, to conclude that controlling the context of interactions between engineers and the generative AI tools is one of the largest challenges they face. The paper concludes with recommendations for mitigating this form of trouble by increasing the ability to control context interactively.

Emma Harvey, Hauke Sandhaus, Abigail Z. Jacobs et al.

Motion capture systems, used across various domains, make body representations concrete through technical processes. We argue that the measurement of bodies and the validation of measurements for motion capture systems can be understood as social practices. By analyzing the findings of a systematic literature review (N=278) through the lens of social practice theory, we show how these practices, and their varying attention to errors, become ingrained in motion capture design and innovation over time. Moreover, we show how contemporary motion capture systems perpetuate assumptions about human bodies and their movements. We suggest that social practices of measurement and validation are ubiquitous in the development of data- and sensor-driven systems more broadly, and provide this work as a basis for investigating hidden design assumptions and their potential negative consequences in human-computer interaction.

A. Feder Cooper, Emanuel Moss, Benjamin Laufer et al.

In 1996, Accountability in a Computerized Society [95] issued a clarion call concerning the erosion of accountability in society due to the ubiquitous delegation of consequential functions to computerized systems. Nissenbaum [95] described four barriers to accountability that computerization presented, which we revisit in relation to the ascendance of data-driven algorithmic systems--i.e., machine learning or artificial intelligence--to uncover new challenges for accountability that these systems present. Nissenbaum's original paper grounded discussion of the barriers in moral philosophy; we bring this analysis together with recent scholarship on relational accountability frameworks and discuss how the barriers present difficulties for instantiating a unified moral, relational framework in practice for data-driven algorithmic systems. We conclude by discussing ways of weakening the barriers in order to do so.

Mona Sloane, Emanuel Moss, Olaitan Awomolo et al.

This paper critically examines existing modes of participation in design practice and machine learning. Cautioning against 'participation-washing', it suggests that the ML community must become attuned to possibly exploitative and extractive forms of community involvement and shift away from the prerogatives of context-independent scalability.