arXiv subjects

Adriana Alvarado Garcia

Publications and source records attributed to Adriana Alvarado Garcia.

6 recordsLinked to original sources

arXiv2026

From Reflection to Repair: A Scoping Review of Dataset Documentation Tools

Dataset documentation is widely recognized as essential for the responsible development of automated systems. Despite growing efforts to support documentation through different kinds of artifacts, little is known about the motivations shaping documentation tool design or the factors hindering their adoption. We present a systematic review supported by mixed-methods analysis of 59 dataset documentation publications to examine the motivations behind building documentation tools, how authors conceptualize documentation practices, and how these tools connect to existing systems, regulations, and cultural norms. Our analysis shows four persistent patterns in dataset documentation conceptualization that potentially impede adoption and standardization: unclear operationalizations of documentation's value, decontextualized designs, unaddressed labor demands, and a tendency to treat integration as future work. Building on these findings, we propose a shift in Responsible AI tool design toward institutional rather than individual solutions, and outline actions the HCI community can take to enable sustainable documentation practices.

cs.SE↗

arXiv2026

Red Teaming LLMs as Socio-Technical Practice: From Exploration and Data Creation to Evaluation

Recently, red teaming, with roots in security, has become a key evaluative approach to ensure the safety and reliability of Generative Artificial Intelligence. However, most existing work emphasizes technical benchmarks and attack success rates, leaving the socio-technical practices of how red teaming datasets are defined, created, and evaluated under-examined. Drawing on 22 interviews with practitioners who design and evaluate red teaming datasets, we examine the data practices and standards that underpin this work. Because adversarial datasets determine the scope and accuracy of model evaluations, they are critical artifacts for assessing potential harms from large language models. Our contributions are first, empirical evidence of practitioners conceptualizing red teaming and developing and evaluating red teaming datasets. Second, we reflect on how practitioners' conceptualization of risk leads to overlooking the context, interaction type, and user specificity. We conclude with three opportunities for HCI researchers to expand the conceptualization and data practices for red-teaming.

cs.CY↗

arXiv2025

Online Safety for All: Sociocultural Insights from a Systematic Review of Youth Online Safety in the Global South

Youth online safety research in HCI has historically centered on perspectives from the Global North, often overlooking the unique particularities and cultural contexts of regions in the Global South. This paper presents a systematic review of 66 youth online safety studies published between 2014 and 2024, specifically focusing on regions in the Global South. Our findings reveal a concentrated research focus in Asian countries and predominance of quantitative methods. We also found limited research on marginalized youth populations and a primary focus on risks related to cyberbullying. Our analysis underscores the critical role of cultural factors in shaping online safety, highlighting the need for educational approaches that integrate social dynamics and awareness. We propose methodological recommendations and a future research agenda that encourages the adoption of situated, culturally sensitive methodologies and youth-centered approaches to researching youth online safety regions in the Global South. This paper advocates for greater inclusivity in youth online safety research, emphasizing the importance of addressing varied sociocultural contexts to better understand and meet the online safety needs of youth in the Global South.

cs.HC↗

arXiv2024

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. 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.

cs.LG↗

arXiv2022

Documenting Data Production Processes: A Participatory Approach for Data Work

The opacity of machine learning data is a significant threat to ethical data work and intelligible systems. Previous research has addressed this issue by proposing standardized checklists to document datasets. This paper expands that field of inquiry by proposing a shift of perspective: from documenting datasets toward documenting data production. We draw on participatory design and collaborate with data workers at two companies located in Bulgaria and Argentina, where the collection and annotation of data for machine learning are outsourced. Our investigation comprises 2.5 years of research, including 33 semi-structured interviews, five co-design workshops, the development of prototypes, and several feedback instances with participants. We identify key challenges and requirements related to the integration of documentation practices in real-world data production scenarios. Our findings comprise important design considerations and highlight the value of designing data documentation based on the needs of data workers. We argue that a view of documentation as a boundary object, i.e., an object that can be used differently across organizations and teams but holds enough immutable content to maintain integrity, can be useful when designing documentation to retrieve heterogeneous, often distributed, contexts of data production.

cs.HC↗

arXiv2020

Civic Technologies: Research, Practice and Open Challenges

Over the last years, civic technology projects have emerged around the world to advance open government and community action. Although Computer-Supported Cooperative Work (CSCW) and Human-Computer Interaction (HCI) communities have shown a growing interest in researching issues around civic technologies, yet most research still focuses on projects from the Global North. The goal of this workshop is, therefore, to advance CSCW research by raising awareness for the ongoing challenges and open questions around civic technology by bridging the gap between researchers and practitioners from different regions. The workshop will be organized around three central topics: (1) discuss how the local context and infrastructure affect the design, implementation, adoption, and maintenance of civic technology; (2) identify key elements of the configuration of trust among government, citizenry, and local organizations and how these elements change depending on the sociopolitical context where community engagement takes place; (3) discover what methods and strategies are best suited for conducting research on civic technologies in different contexts. These core topics will be covered across sessions that will initiate in-depth discussions and, thereby, stimulate collaboration between the CSCW research community and practitioners of civic technologies from both Global North and South.

cs.CY↗