Gabrielle Benabdallah

Gabrielle Benabdallah

Explainable AI (XAI) interfaces seek to make large language models more transparent, yet explanation alone does not produce understanding. Explaining a system's behavior is not the same as being able to engage with it, to probe and interpret its operations through direct manipulation. This distinction matters for scientific disciplines in particular: scientists who increasingly rely on LLMs for reading, citing, and producing literature reviews have little means of directly engaging with how these models process and transform the texts they generate. In this ongoing design research project, I argue for a shift from explainability to interpretative engagement. This shift moves away from accounts of system behavior to instead enable users to manipulate a model's intermediate representations. Drawing on textual scholarship, computational poetics, and the history of reading and writing technologies, including practices such as marginalia, glosses, indices, and annotation systems, I propose interpretative interfaces as interactive environments in which non-expert users can intervene in the representational space of a language model. More specifically, such interfaces will allow users to select a token and follow its trajectory through the model's intermediate layers. This way, they can observe how its semantic position shifts as context is processed, and possibly annotate the transformations they find useful or meaningful. The same way readers can create their own maps within a book through annotations and bookmarks, interpretative interfaces will allow users to inscribe their reading of a model's internal representations. The goal of this project is to reframe AI interpretability as an interaction design project rather than a purely technical one, and to open a path toward AI-mediated reading that supports interpretative engagement and critical stewardship of scientific knowledge.

Gabrielle Benabdallah, Samuelle Bourgault, Nadya Peek et al.

Digital fabrication courses that relied on physical makerspaces were severely disrupted by COVID-19. As universities shut down in Spring 2020, instructors developed new models for digital fabrication at a distance. Through interviews with faculty and students and examination of course materials, we recount the experiences of eight remote digital fabrication courses. We found that learning with hobbyist equipment and online social networks could emulate using industrial equipment in shared workshops. Furthermore, at-home digital fabrication offered unique learning opportunities including more iteration, machine tuning, and maintenance. These opportunities depended on new forms of labor and varied based on student living situations. Our findings have implications for remote and in-person digital fabrication instruction. They indicate how access to tools was important, but not as critical as providing opportunities for iteration; they show how remote fabrication exacerbated student inequities; and they suggest strategies for evaluating trade-offs in remote fabrication models with respect to learning objectives.