Recent Large Language Model (LLM) based AI can exhibit recognizable and measurable personality traits during conversations to improve user experience. However, as human understandings of their personality traits can be affected by their interaction partners’ traits, a potential risk is that AI traits may shape and bias users’ self-concept of their own traits. To explore the possibility, we conducted a randomized behavioral experiment. Our results indicate that after conversations about personal topics with an LLM-based AI chatbot using GPT-4o default personality traits, users’ self-concepts aligned with the AI’s measured personality traits. The longer the conversation, the greater the alignment. This alignment led to increased homogeneity in self-concepts among users. We also observed that the degree of self-concept alignment was positively associated with users’ conversation enjoyment. Our findings uncover how AI personality traits can shape users’ self-concepts through human-AI conversation, highlighting both risks and opportunities. We provide important design implications for developing more responsible and ethical AI systems.

Existing conversational search systems can synthesize information into responses, but they lack principled ways to adapt response formats to users’ cognitive states. This paper investigates whether aligning format and distance, which involves matching information granularity and media to users’ psychological distance, improves user experience. In a between-subjects experiment (N = 464) on travel planning, we crossed two distance dimensions (temporal/spatial × near/far) with four formats varying in granularity (abstract/concrete) and media (text/image-and-text). The experiment established that format–distance alignment reduced users’ risk perceptions while increasing decision confidence, perceptions of information usefulness, ease of use, enjoyment, and credibility, and adoption intentions. Concrete formats imposed higher cognitive load, but yielded productive effort when matched to near-distance tasks. Images enhanced concrete but not abstract text, suggesting multimedia benefits depend on complementarity. These findings establish format–distance alignment as a distinctive and important design dimension, enabling systems to tailor response formats to users’ psychological distance.

Qualitative coding is a demanding yet crucial research method in the field of Human–Computer Interaction (HCI). While recent studies have shown the capability of Large Language Models (LLMs) to perform qualitative coding within theoretical frameworks, their potential for collaborative human-LLM discovery and generation of new insights beyond initial theory remains underexplored. To bridge this gap, we proposed CHALET , a novel approach that harnesses the power of human-LLM partnership to advance theory-driven qualitative analysis by facilitating iterative coding, disagreement analysis, and conceptualization of qualitative data. We demonstrated CHALET ’s utility by applying it to the qualitative analysis of conversations related to mental-illness stigma, using the attribution model as the theoretical framework. Results highlighted the unique contribution of human-LLM collaboration in uncovering latent themes of stigma across the cognitive, emotional, and behavioral dimensions. We discuss the methodological implications of the human-LLM collaborative approach to theory-based qualitative analysis for the HCI community and beyond.

Mental-health stigma remains a pervasive social problem that hampers treatment-seeking and recovery. Existing resources for training neural models to finely classify such stigma are limited, relying primarily on social-media or synthetic data without theoretical underpinnings. To remedy this gap, we present an expert-annotated, theory-informed corpus of human-chatbot interviews, comprising 4,141 snippets from 684 participants with documented socio-cultural backgrounds. Our experiments benchmark state-of-the-art neural models and empirically unpack the challenges of stigma detection. This dataset can facilitate research on computationally detecting, neutralizing, and counteracting mental-health stigma. Our corpus is openly available at https://github.com/HanMeng2004/Mental-Health-Stigma-Interview-Corpus.

World models for autonomous driving have the potential to dramatically improve the reasoning capabilities of today's systems. However, most works focus on camera data, with only a few that leverage lidar data or combine both to better represent autonomous vehicle sensor setups. In addition, raw sensor predictions are less actionable than 3D occupancy predictions, but there are no works examining the effects of combining both multimodal sensor data and 3D occupancy prediction. In this work, we perform a set of experiments with a MUltimodal World Model with Geometric VOxel represen-tations (MUVO) to evaluate different sensor fusion strategies to better understand the effects on sensor data prediction. We also analyze potential weaknesses of current sensor fusion approaches and examine the benefits of additionally predicting 3D occupancy.

Non-native speakers (NNSs) often face speaking challenges in real-time multilingual communication, such as struggling to articulate their thoughts. To address this issue, we developed an AI-based speaking assistant (AISA) that provides speaking references for NNSs based on their input queries, task background, and conversation history. To explore NNSs' interaction with AISA and its impact on NNSs' speaking during real-time multilingual communication, we conducted a mixed-method study involving a within-subject experiment and follow-up interviews. In the experiment, two native speakers (NSs) and one NNS formed a team (31 teams in total) and completed two collaborative tasks-one with access to the AISA and one without. Overall, our study revealed four types of AISA input patterns among NNSs, each reflecting different levels of effort and language preferences. Although AISA did not improve NNSs' speaking competence, follow-up interviews revealed that it helped improve the logical flow and depth of their speech. Moreover, the additional multitasking introduced by AISA, such as entering and reviewing system output, potentially elevated NNSs' workload and anxiety. Based on these observations, we discuss the pros and cons of implementing tools to assist NNS in real-time multilingual communication and offer design recommendations.

Emergence of new hardware, including persistent memory and smart network interface card (SmartNIC), has brought new opportunities to file system design. In this paper, we design and implement a new file system named NICFS based on persistent memory and SmartNIC. We divide the file system into two parts: the front end and the back end. In the front end, data writes are appended to the persistent memory in a log-structured way, leveraging the fast persistence advantage of persistent memory. In the back end, the data in logs are fetched, processed, and patched to files in the background, leveraging the processing capacity of SmartNIC. Evaluation results show that NICFS outperforms Ext4 by about 21%/10% and about 19%/50% on large and small reads/writes, respectively.