Professional self-representation involves constructing identities that reflect personal values while aligning with the norms of professional communities. Many people turn to generative AI for help, but misalignments between LLM outputs and self-understanding hinder authenticity and accuracy of the content. To explore how LLMs can support co-creation aligned, authentic self-representational content, we designed LL.me, a web-based probe based on bi-directional alignment that utilizes users’ resumes and guides them through iterative cycles of refining AI-generated self-representations. Our user study with 14 participants showed users engaged in identity work with the tool, re-framing content to emphasize their personal values, imparting tacit knowledge from their communities of practice, and leveraging system explainability features as a proxy for how the representation would be perceived by others. We demonstrate how LLM-based tools can facilitate a co-constructive process of identity formation, helping individuals actively shape their professional self-representations in collaboration with the AI.

Large Language Models are often trained on data reflecting neurotypical norms, yet are increasingly deployed to support neurodivergent users in sensitive domains like job-seeking.We examine interactions between neurodivergent job-seekers and a GPT-4powered career support chatbot through the lens of misalignment.Through analysis of over 300 chat logs and interviews with 15 neurodivergent participants, we found that the chatbot frequently misrepresented users' skills, imposed neurotypical language and expectations, and provided generic or inappropriate advice-even when relevant user data was available.Participants expected the chatbot to interpret implicit insights from their data, however, they sometimes lacked the clarity or confidence to correct the system when it did not, revealing gaps in both AI design and user understanding of system function.Our findings underscore the need for bi-directional alignment between neurodivergent users and LLMs, and call for design strategies that integrate neurodivergent perspectives and preferences to ensure more authentic, personalized, and human-centered AI support.

Abstract Reinforcement learning (RL) systems can be complex and non-interpretable, making it challenging for non-AI experts to understand or intervene in their decisions. This is due in part to the sequential nature of RL in which actions are chosen because of their likelihood of obtaining future rewards. However, RL agents discard the qualitative features of their training, making it difficult to recover user-understandable information for “why” an action is chosen. We propose a technique Experiential Explanations to generate counterfactual explanations by training influence predictors along with the RL policy. Influence predictors are models that learn how different sources of reward affect the agent in different states, thus restoring information about how the policy reflects the environment. Two human evaluation studies revealed that participants presented with Experiential Explanations were better able to correctly guess what an agent would do than those presented with other standard types of explanation. Participants also found that Experiential Explanations are more understandable, satisfying, complete, useful, and accurate. Qualitative analysis provides information on the factors of Experiential Explanations that are most useful and the desired characteristics that participants seek from the explanations.

Supported employment programs have demonstrated the ability to enhance employment outcomes for neurodivergent individuals by offering personalized job coaching that aligns with the strengths of each individual. While various technological interventions have been designed to support these programs, technologies that hyperfocus on users’ assumed challenges through deficit-based design have been criticized due to their potential to undermine the agency of neurodivergent individuals. Therefore, we use strengths-based co-design to explore the opportunities for a technology that supports neurodivergent employees using their strengths. The co-design activities uncovered our participants’ current strategies to address workplace challenges, the strengths they employ, and the technology designs that our participants developed to operationalize those strengths in a supportive technology. We find that incorporating strengths-based strategies for emotional regulation, interpersonal problem solving, and learning job-related skills can provide a supportive technology experience that bolsters neurodiverse employees’ agency and independence in the workplace. In response, we suggest design implications for using neurodiverse strengths as design requirements and how to design for independence in workplace.

Co-design of technology encourages participation and decision-making input of end-users. In the case of technologies for individuals with Intellectual and Developmental Disabilities (IDD), the end-users are historically left out of the design process. Further deepening the disconnect between this group and technology, they are also excluded from formal technology design knowledge sharing, such as college courses. To address this, our study investigates the efficacy of a formal classroom adaptation of co-design activities to encourage learning and participation. Through collaboration between educators and designers, we adopted user-centered co-design activities to facilitate knowledge and application of technological design methods within a class of 13 students with IDD. Findings uncovered factors contributing to co-teaching collaboration planning and reflection between educators and designers, and ways that activities can provide accessible collaborative learning environments for students with IDD by supporting collaboration, cognitive engagement, and meta-cognition. We discuss how these factors can support successful co-teacher collaborations that promote student empowerment. Finally, we contribute collaborative co-teaching strategies for educational co-design activities for individuals with IDD.

Inclusive workplaces require mutual efforts between neurotypical (NT) and neurodivergent (ND) employees to understand one another’s viewpoints and experiences. Currently, the majority of inclusivity training places the burden of change on NDs to conform to NT social-behavioral standards. Our research examines moving toward a more equal effort distribution by exploring virtual reality (VR) design opportunities to build NTs’ understanding of ND workplace experiences. Using participatory design, including generative toolkits and design meetings, we surfaced two main themes that could bridge gaps in understanding: (1) NTs’ recognition of NDs’ strengths and efforts at work, and (2) NTs’ understanding of NDs’ differences. We present a strengths-based assessment of ND traits in the workplace, focusing on how workplaces can support NDs’ success. Finally, we propose VR simulation designs that communicate these themes to represent ND experiences, emphasizing their strengths and viewpoints so that NT co-workers can better empathize and accommodate them.

While birth control pills are one of the most common forms of contraception, their usage has several emotional and physical costs, such as taking the pill daily and experiencing hormonal side effects. The burden of these tasks in relationships generally falls on the pill user with minimal involvement from their partner. In this study, we conducted semi-structured interviews with pill users and their partners to investigate the differences between their perceived current and ideal divisions of birth control responsibility. During the interview, we presented a collaborative birth control tracking app prototype to examine how such technology can overcome these discrepancies. We found that pill users were unsatisfied with their partners' engagement in contraceptive tasks but did not communicate this well. Meanwhile, partners wanted to contribute more to pregnancy prevention but did not know how. When presented with our app prototype, users and partners stated that our design could address these issues by improving communication between users and partners. In particular, users appreciated how technology could increase engagement and support from their partner, and partners liked that our app presented several concrete ways to become more involved and show emotional support. However, privacy issues exist given the sensitive nature of contraception. We highlight design considerations that should be kept in mind about privacy while recognizing pill users' efforts and promoting partners' involvement.

Contact tracers assist in containing the spread of highly infectious diseases such as COVID-19 by engaging community members who receive a positive test result in order to identify close contacts. Many contact tracers rely on community member’s recall for those identifications, and face limitations such as unreliable memory. To investigate how technology can alleviate this challenge, we developed a visualization tool using de-identified location data sensed from campus WiFi and provided it to contact tracers during mock contact tracing calls. While the visualization allowed contact tracers to find and address inconsistencies due to gaps in community member’s memory, it also introduced inconsistencies such as false-positive and false-negative reports due to imperfect data, and information sharing hesitancy. We suggest design implications for technologies that can better highlight and inform contact tracers of potential areas of inconsistencies, and further present discussion on using imperfect data in decision making.