AI in UX: Can You Trust it? What Works and What Breaks?
TorCHI presents 5 presentation previews headed to CHI 2026 in Barcelona. One of the most selective and prestigious conferences in human-computer interaction, these presentations explore critical questions at the intersection of AI, UX research, and design, from the risks of misleading LLMs to new approaches for collaboration and creative practice.
Hosted at the University of Toronto’s DGP Research Lab, this is a rare opportunity to engage directly with the researchers behind these groundbreaking work.
Date: Monday April 6, 2026,
Time: 7pm – 9pm (Toronto, please arrive early for light refreshments)
Location: DGP Lab, Bahen Centre, 40 St. George St., Room 5187, Toronto, ON
Capacity is limited so please register early. Thank you.
5 PRESENTATIONS:
1. Invisible Saboteurs: Sycophantic LLMs Mislead Novices in Problem-Solving Tasks, by Jessica Y. Bo, et al.
Sycophancy, the tendency of LLM-based chatbots to express excessive agreement with their users, even when inappropriate, is emerging as a significant risk in human-AI interactions. However, the extent to which this affects human-LLM collaboration in complex problem-solving tasks is not well quantified, especially among novices who are prone to misconceptions. We created two LLM chatbots, one with high sycophancy and one with low sycophancy, and conducted a within-subjects experiment (n=24) in the context of debugging machine learning models to investigate the effect of sycophancy on users' mental models, workflows, reliance behaviors, and perceptions of the chatbots. Our findings show that users of the high sycophancy chatbot were less likely to correct their misconceptions and spent more time over-relying on unhelpful LLM responses, leading them to significantly worse performance in the task. Despite these impaired outcomes, a majority of users were unable to detect the presence of excessive sycophancy. https://arxiv.org/abs/2510.03667
2. The Promises and Perils of using LLMs for Effective Public Services, by Erina Moon, et al.
Governments are the primary providers of essential public services and are responsible for delivering them effectively. In high-stakes decision-making domains such as child welfare (CW), agencies must protect children without unnecessarily prolonging a family's engagement with the system. With growing optimism around AI, governments are pushing for its integration but concerns regarding feasibility and harms remain. Through collaborations with a large Canadian CW agency, we examined how LocalLLM and BERTopic models can track CW case progress. We demonstrate how the tools can potentially assist workers in opportunistically addressing gaps in their work by signaling case progress/deviations. And yet, we also show how they fail to detect case trajectories that require discretionary judgments grounded in social work training, areas where practitioners would actually want support to pre-emptively address substantive case concerns. We also provide a roadmap of future participatory directions to co-design language tools for/with the public sector. https://arxiv.org/abs/2601.15163
3. SoundStager: Interactive Design of Story-Driven GenAI Soundscapes for Video, by Suhyeon Yoo, et al.
Sound effects (SFX) are critical to video storytelling by immersing viewers, directing attention, and shaping emotion. However, crafting an effective soundscape is difficult: creators must decidehow to source, place, layer, and mix sounds to support the narrative. Generative text-to-SFX tools enable users to create custom sounds, but creators often struggle to describe sounds with words and lack control over individual stems in premixed outputs.
We propose SoundStager, an AI-assisted tool for designing generative soundscapes for video. SoundStager analyzes the video narrativeto create layered audio scenes (of keynote, signal, soundmark, and archetypal sounds) and supports iterative refinement through a combination of conversational and analog controls. Our user evaluation with twelve video creators shows that SoundStager enables users to quickly create satisfactory soundscapes while retaining creative control. https://ccrma.stanford.edu/~urinieto/MARL/publications/CHI26-soundstager.pdf
4. Reflexis: Supporting Reflexivity and Rigor in Collaborative Qualitative Analysis through Design for Deliberation, by Runlong Ye, et al.
Reflexive Thematic Analysis (RTA) is a critical method for generating deep interpretive insights. Yet its core tenets, including researcher reflexivity, tangible analytical evolution, and productive disagreement, are often poorly supported by software tools that prioritize speed and consensus over interpretive depth. To address this gap, we introduce Reflexis, a collaborative workspace that centers these practices. It supports reflexivity by integrating in-situ reflection prompts, makes code evolution transparent and tangible, and scaffolds collaborative interpretation by turning differences into productive, positionality-aware dialogue. Results from our paired-analyst study ( = 12) indicate that Reflexis encouraged participants toward more granular reflection and reframed disagreements as productive conversations. The evaluation also surfaced
key design tensions, including a desire for higher-level, networked memos and more user control over the timing of proactive alerts. Reflexis contributes a design framework for tools that prioritize rigor and transparency to support deep, collaborative interpretation in an age of automation. https://arxiv.org/abs/2601.15445
5. GroundLink: Exploring How Contextual Meeting Snippets Can Close Common Ground Gaps in Editing 3D Scenes for Virtual Production, by Warren Park, et al.
Virtual Production (VP) professionals often face challenges accessing tacit knowledge and creative intent, which are important in forming common ground with collaborators and in contributing more effectively and efficiently to the team. From our formative study (N=23) with a follow-up interview (N=6), we identified the significance and prevalence of this challenge. To help professionals access knowledge, we present GroundLink, a Unity add-on that surfaces meeting-derived knowledge directly in the editor to support establishing common ground. It features a meeting knowledge dashboard for capturing and reviewing decisions and comments, constraint-aware feedforward that proactively informs the editor environment, and cross-modal synchronization that provides referential links between the dashboard and the editor. A comparative study (N=12) suggested that GroundLink helps users build common ground with their team while improving perceived confidence and ease of editing the 3D scene. An expert evaluation with VP professionals (N=5) indicated strong potential for GroundLink in real-world workflows.
https://arxiv.org/abs/2602.12987