Source note2 min read
It's Complicated: On the Design and Evaluation of AI-Powered AAC Interfaces
Source
arXiv
arxiv.org/abs/2606.24854v1
Source
- Source name: arXiv
- Source kind: paper
- Authors / organization: Blade Frisch, Will Wade, Dylan Gaines, Michelle Kinsella, Betts Peters, Tamara Broderick, Keith Vertanen
- Venue: arXiv: cs.HC
- Published: 2026-06-23
- Collected: 2026-06-24
- URL: http://arxiv.org/abs/2606.24854v1
- PDF: https://arxiv.org/pdf/2606.24854v1
- DOI: UNKNOWN
Plain-Language Brief
The paper discusses the challenges in evaluating AI-powered augmentative and alternative communication (AAC) systems due to the complexity of human needs and desires. It proposes six AAC problem spaces, potential AI solutions, and improved evaluation methods that consider individual's intersectional nuances.
What the Document Says
- AI can enhance AAC systems
- Evaluation of AI-powered AAC interfaces is difficult due to human complexity
- The paper explores six AAC problem spaces
- Potential AI usage in these six AAC problem spaces is discussed
- More robust evaluation methods are suggested considering intersectional nuances
Key Concepts Mentioned
- artificial intelligence
- augmentative and alternative communication (AAC)
- evaluation
- intersectionality
- problem spaces
Claims Made by the Document
- AI can enhance AAC systems
- Current evaluation metrics struggle to capture human complexity
- Proposed evaluation methods consider intersectional nuances
Evidence Used
- The paper discusses the potential benefits of AI for AAC systems and the challenges in evaluating them.
Methods / Approach
- Exploration of six AAC problem spaces, discussion of potential AI solutions, and proposal of improved evaluation methods
Limitations Stated by the Authors
The paper does not provide specific examples or case studies of AI-powered AAC interfaces.
Limitations Noted by the Agent
Agent interpretation — not from the source.
The paper is a research paper and may lack practical implementation details or real-world testing results.
Open Questions
- What are the specific AI techniques being proposed for each AAC problem space?
- How effective are these proposed evaluation methods in practice?
Notes for Future Q&A
May include interpretation. Labeled where it does.
The paper does not provide details about the specific AI techniques being proposed for each AAC problem space. The effectiveness of the proposed evaluation methods in practice is also unknown.
Raw Abstract / Excerpt
Artificial intelligence (AI) can enhance what people who use augmentative and alternative communication (AAC) are able to do with their systems. However, evaluating AI-powered AAC interfaces can be difficult. People are intersectional beings and current evaluation metrics can struggle to capture the multifaceted and nuanced desires people may have for their AAC. We explore the complicated nature of six AAC problem spaces, explore how AI might be used in these spaces, and suggest more robust methods of evaluation that take the intersectional nuances of people into account. We also discuss broader issues that arise across these problem spaces and how they could be addressed using our proposed evaluation methods.
