Searcharxiv⌕ Search

arXiv subjects

Emanuel Moss

Publications and source records attributed to Emanuel Moss.

15 recordsLinked to original sources
arXiv2026

Context and Symmetry in Auditing: A Case Study of Skeleton Inference in Motion Capture

Humans are increasingly expected to interact with AI systems that observe and make inferences about them - but do these systems actually work? A standard approach to answering this question is AI auditing. Conducting an AI audit requires identifying how a system behaves (i.e., determining what types of inputs to audit it with and then observing and documenting actual system behavior) and contrasting that with how a system should behave (i.e., determining what the nominal outputs of a system should look like). We argue that this is best done through a contextual audit, which we introduce as a method for auditing measurements within the context of the practices that produce them. We show how contextual auditing enables the interrogation of assumptions implicit in the audit process and allows auditors to be explicit about what serves as ground truth, which we define as verifiable measurements about the real world against which systems are evaluated. We outline how the concept of symmetry from science and technology studies can enable audits when ground truth is unknown, unknowable, or contested. Finally, to demonstrate how contextual and symmetric audits can be conducted in practice, we present a case study of skeleton inference in motion capture and propose areas suggested by our case study as particularly fruitful for future audits of motion capture systems.

cs.CY↗
arXiv2026

Context Collapse: Barriers to Adoption for Generative AI in Workplace Settings

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.

cs.CY↗
arXiv2025

Controlling Context: Generative AI at Work in Integrated Circuit Design and Other High-Precision Domains

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.

cs.HC↗
arXiv2025

Thoughts without Thinking: Reconsidering the Explanatory Value of Chain-of-Thought Reasoning in LLMs through Agentic Pipelines

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.

cs.AI↗
arXiv2025

What's So Human about Human-AI Collaboration, Anyway? Generative AI and Human-Computer Interaction

While human-AI collaboration has been a longstanding goal and topic of study for computational research, the emergence of increasingly naturalistic generative AI language models has greatly inflected the trajectory of such research. In this paper we identify how, given the language capabilities of generative AI, common features of human-human collaboration derived from the social sciences can be applied to the study of human-computer interaction. We provide insights drawn from interviews with industry personnel working on building human-AI collaboration systems, as well as our collaborations with end-users to build a multimodal AI assistant for task support.

cs.HC↗
arXiv2025

ACE, Action and Control via Explanations: A Proposal for LLMs to Provide Human-Centered Explainability for Multimodal AI Assistants

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.

cs.HC↗
arXiv2024

Introducing v0.5 of the AI Safety Benchmark from MLCommons

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.

cs.CL↗
arXiv2024

Materiality and Risk in the Age of Pervasive AI Sensors

Artificial intelligence (AI) systems connected to sensor-laden devices are becoming pervasive, which has notable implications for a range of AI risks, including to privacy, the environment, autonomy and more. There is therefore a growing need for increased accountability around the responsible development and deployment of these technologies. Here we highlight the dimensions of risk associated with AI systems that arise from the material affordances of sensors and their underlying calculative models. We propose a sensor-sensitive framework for diagnosing these risks, complementing existing approaches such as the US National Institute of Standards and Technology AI Risk Management Framework and the European Union AI Act, and discuss its implementation. We conclude by advocating for increased attention to the materiality of algorithmic systems, and of on-device AI sensors in particular, and highlight the need for development of a sensor design paradigm that empowers users and communities and leads to a future of increased fairness, accountability and transparency.

cs.CY↗
arXiv2024

The Cadaver in the Machine: The Social Practices of Measurement and Validation in Motion Capture Technology

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.

cs.CY↗
arXiv2023

Datasheets for Machine Learning Sensors

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.

cs.LG↗
arXiv2022

The Objective Function: Science and Society in the Age of Machine Intelligence

Machine intelligence, or the use of complex computational and statistical practices to make predictions and classifications based on data representations of phenomena, has been applied to domains as disparate as criminal justice, commerce, medicine, media and the arts, mechanical engineering, among others. How has machine intelligence become able to glide so freely across, and to make such waves for, these domains? In this dissertation, I take up that question by ethnographically engaging with how the authority of machine learning has been constructed such that it can influence so many domains, and I investigate what the consequences are of it being able to do so. By examining the workplace practices of the applied machine learning researchers who produce machine intelligence, those they work with, and the artifacts they produce. The dissertation begins by arguing that machine intelligence proceeds from a naive form of empiricism with ties to positivist intellectual traditions of the 17th and 18th centuries. This naive empiricism eschews other forms of knowledge and theory formation in order for applied machine learning researchers to enact data performances that bring objects of analysis into existence as entities capable of being subjected to machine intelligence. By data performances, I mean generative enactments which bring into existence that which machine intelligence purports to analyze or describe. The enactment of data performances is analyzed as an agential cut into a representational field that produces both stable claims about the world and the interpretive frame in which those claims can hold true. The dissertation also examines how machine intelligence depends upon a range of accommodations from other institutions and organizations, from data collection and processing to organizational commitments to support the work of applied machine learning researchers.

cs.CY↗
arXiv2022

A relationship and not a thing: A relational approach to algorithmic accountability and assessment documentation

Central to a number of scholarly, regulatory, and public conversations about algorithmic accountability is the question of who should have access to documentation that reveals the inner workings, intended function, and anticipated consequences of algorithmic systems, potentially establishing new routes for impacted publics to contest the operations of these systems. Currently, developers largely have a monopoly on information about how their systems actually work and are incentivized to maintain their own ignorance about aspects of how their systems affect the world. Increasingly, legislators, regulators and advocates have turned to assessment documentation in order to address the gap between the public's experience of algorithmic harms and the obligations of developers to document and justify their design decisions. However, issues of standing and expertise currently prevent publics from cohering around shared interests in preventing and redressing algorithmic harms; as we demonstrate with multiple cases, courts often find computational harms non-cognizable and rarely require developers to address material claims of harm. Constructed with a triadic accountability relationship, algorithmic impact assessment regimes could alter this situation by establishing procedural rights around public access to reporting and documentation. Developing a relational approach to accountability, we argue that robust accountability regimes must establish opportunities for publics to cohere around shared experiences and interests, and to contest the outcomes of algorithmic systems that affect their lives. Furthermore, algorithmic accountability policies currently under consideration in many jurisdictions must provide the public with adequate standing and opportunities to access and contest the documentation provided by the actors and the judgments passed by the forum.

cs.CY↗
arXiv2022

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

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.

cs.CY↗
arXiv2020

Participation is not a Design Fix for Machine Learning

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.

cs.CY↗