Mengqi Shi

Mengqi Shi, Haopeng Zhang

While Multimodal Large Language Models (MLLMs) exhibit strong performance on standard video tasks, their ability to faithfully summarize and reason over complex narratives remains poorly evaluated. Existing summarization benchmarks fragment supervision across isolated granularities, such as keyframes, key shots, or disjointed text summaries, failing to capture the inherently hierarchical structure of cross-modal alignment. To address this critical gap, we introduce HAVEN, a hierarchically aligned multimodal benchmark for unified video understanding. HAVEN pioneers a fully granular (frame, shot, and video levels) and fully multimodal (video and text) dataset architecture, complete with explicit, continuous alignment between modalities. Built upon this unified annotation paradigm, we propose a comprehensive evaluation suite spanning summarization, temporal reasoning, multimodal grounding, and saliency ranking. Extensive benchmarking of state-of-the-art MLLMs exposes a persistent gap between surface-level textual fluency and grounded multimodal understanding. Ultimately, HAVEN advances the evaluation of multimodal systems beyond traditional QA formats, offering a rigorous, standardized testbed to drive future research in interpretable, hierarchical video understanding. We publicly release the dataset, benchmark suite, and evaluation protocols.

Mengqi Shi, Tianqi Song, Zicheng Zhu et al.

Older adults have increasingly turned to conversational AI as a source of emotional support. However, little is known about how emotionally supportive interactions are experienced in everyday use, particularly when AI systems limit, redirect, or intervene during these interactions. We interviewed 18 older adults about their experiences using conversational AI for emotional support, examining when they turn to AI, how they engage during emotionally vulnerable moments, and how they respond when support feels disrupted. Our findings show that older adults often rely on AI when other forms of social support feel inaccessible. However, current safety-related interventions can redirect interactions in ways that participants experience as interruptions to emotional engagement or as shifts in control away from them. Such disruptions can undermine older adults' ability to remain emotionally engaged and, in some cases, contribute to emotional distress. We discussed design implications for emotionally supportive conversational AI, emphasizing the need for safety interventions that are enacted within older adults' social contexts, align with users' emotional pacing, and preserve their sense of agency.

Mengqi Shi

The rapid advancement of AI companionship systems has positioned them as scalable interventions for addressing social isolation. Current design approaches emphasize maximizing user engagement and satisfaction, treating effective alignment between AI capabilities and user needs as an unqualified success. However, this framing may overlook a critical dimension of bidirectional human-AI alignment: when AI systems successfully align with users' expressed emotional needs, users may reciprocally adapt their relational expectations in ways that undermine authentic human connection and agency. We examine what we term the authenticity paradox: the phenomenon whereby successful bidirectional alignment in emotionally supportive AI paradoxically harms the values that motivated the intervention. Through the analysis of AI companionship for older adults as an illustrative case, we identify four key tensions that emerge when technical effectiveness generates ethical concerns: the dilemma of AI becoming users' only accessible option, mismatches between emotional needs and system-level interventions, conflicts over sense of control during vulnerable moments, and fundamental disagreements about whose values should guide system behavior.