Large language models (LLMs) trained on real-world data can inadvertently reflect harmful societal biases, particularly toward historically marginalized communities. While previous work has primarily focused on harms related to age and race, emerging research has shown that biases toward disabled communities exist. This study extends prior work exploring the existence of harms by identifying categories of LLM-perpetuated harms toward the disability community. We conducted 19 focus groups, during which 56 participants with disabilities probed a dialog model about disability and discussed and annotated its responses. Participants rarely characterized model outputs as blatantly offensive or toxic. Instead, participants used nuanced language to detail how the dialog model mirrored subtle yet harmful stereotypes they encountered in their lives and dominant media, e.g., inspiration porn and able-bodied saviors. Participants often implicated training data as a cause for these stereotypes and recommended training the model on diverse identities from disability-positive resources. Our discussion further explores representative data strategies to mitigate harm related to different communities through annotation co-design with ML researchers and developers.
This study examined how to design tools that build independence with Blind or Visually Impaired (BVI) children and their families. Beyond core academics, BVI children require instruction on independent living skills, with their curriculum necessitating parent-school cooperation to support continued education at home. However, most technology for BVI children focus on academics, spatial orientation, and physical mobility. In this work, we aim to design a tool for independence that aligns with existing familial structures and activities. Through interviews and diary studies with five families, we explored development practices parents used with their BVI children, parent-teacher relationships, and how a prompting and reflection tool supported family goals. This study highlights home routines and independence skills that benefit from customized prompting, how activity prompts can encourage parents to scale back their assistance and propel independence, and how reflection builds optimism and empowers parents in the learning process.