Generative information retrieval (GenIR) enables users to obtain synthesized information through iterative interaction with LLMs, fundamentally reshaping how AI-generated content is produced and consumed. Within this shift, users may encounter AI-generated informational content through two primary pathways: actively creating it themselves or consuming content generated by others. We examine whether authorship biases evaluation---whether users judge AI output from their own interactions more favorably than equivalent output from others. In a mixed-methods experiment (N=28, 2×2 within-subjects), participants interacted with an AI system to retrieve and craft information, then evaluated both their own result and equivalent output generated through the same process but framed as someone else's. Results reveal a selective authorship bias: participants rated self-obtained information significantly higher in quality, but showed no corresponding difference in trust. This pattern suggests that hallucination-aware skepticism constrained trust judgments, but could not prevent quality-driven selection behavior, even in the presence of information conflicts. Given that iterative interactions are inherent to GenIR, diverse interventions seem needed to support users' critical evaluation.

Conversational shopping agents powered by large language models are increasingly used for online product exploration, yet the role of interaction style in shaping shopping behavior and user experience remains underexplored in shopping IR. To address the gap, we conducted two studies in experience-goods domains. Study 1 involved 24 participants and compared a neutral conversational agent with a traditional product search interface, confirming functional adequacy and identifying two unmet needs, self-reflective preference structuring and socially grounded relational guidance. Study 2 involved 30 participants and evaluated two personas derived from these needs, Self-Mirroring and Relational Peer, against the same neutral agent in a within-subjects design with information availability held constant. Self-Mirroring increased critical thinking scores and sustained follow-up questioning of retrieved content, whereas Relational Peer increased social presence while reducing explicit verification behaviors such as comparing alternatives and checking conditions. The discussion outlines implications for AI shopping agents that adapt interaction style to decision context, balancing efficient exploration with user-led evaluation.

Conversational argument search systems influence how users access diverse perspectives but are prone to selective exposure. To address this, we propose two strategies: an interface-level multi-agent framework that structures perspective presentation and an interaction-level questioning strategy that encourages deeper engagement. We evaluate these strategies through a 2 x 2 factorial user study, examining their impact on selective exposure. Results show that the multi-agent setup facilitates broader perspective comparison, while agent-initiated questioning fosters deeper reflection; together, they promote more balanced argument access. Based on these findings, we discuss conversational search systems to mitigate selective exposure by implementing multi-agent interactions and questioning mechanisms.

The adoption of generative AI technologies is swiftly expanding. Services employing both linguistic and multimodal models are evolving, offering users increasingly precise responses. Consequently, human reliance on these technologies is expected to grow rapidly. With the premise that people will be impacted by the output of AI, we explored approaches to help AI output produce better results. Initially, we evaluated how contemporary AI services competitively meet user needs, then examined society's depiction as mirrored by Large Language Models (LLMs). We did a query experiment, querying about social conventions in various countries and eliciting a one-word response. We compared the LLMs' value judgments with public data and suggested a model of decision-making in value-conflicting scenarios which could be adopted for future machine value judgments. This paper advocates for a practical approach to using AI as a tool for investigating other remote worlds. This research has significance in implicitly rejecting the notion of AI making value judgments and instead arguing a more critical perspective on the environment that defers judgemental capabilities to individuals. We anticipate this study will empower anyone, regardless of their capacity, to receive safe and accurate value judgment-based outputs effectively.

The self-reference effect is a psychological phenomenon where information relating to oneself is processed more deeply and remembered more effectively than other information. We propose "self-referential reviews," crafted by merging personal information with existing reviews using the novel "Self-Referential ReviewMaker" prototype, which leverages Large Language Models (LLMs). The essence of the "self-referential review" lies in harnessing the self-reference effect, making the readers feel as if they are the protagonist of the review. To validate the efficacy of self-referential reviews, we conducted a user study focusing on online reviews with thirty-four participants. The contributions of our paper are centered around self-referential reviews, highlighting (1) the creation of these reviews using our new prototype, Self-Referential ReviewMaker, (2) their effectiveness in enhancing review helpfulness through the self-reference effect, and (3) the identification of additional factors influencing the self-reference effect with further discussion on enhancing user-focused review systems.

Studies on supervised machine learning (ML) recommend involving workers from various backgrounds in training dataset labeling to reduce algorithmic bias. Moreover, sophisticated tasks for categorizing objects in images are necessary to improve ML performance, further complicating micro-tasks. This study aims to develop a task design incorporating the fair participation of people, regardless of their specific backgrounds or task’s difficulty. By collaborating with 75 labelers from diverse backgrounds for 3 months, we analyzed workers’ log-data and relevant narratives to identify the task’s hurdles and helpers. The findings revealed that workers’ decision-making tendencies were affected by the "community" that positively helps workers. Also, the machine’s feedback perceived by workers could make people easily engaged in works. Based on these findings, we suggest an extended human-in-the-loop approach that connects labelers, machines, and communities rather than isolating individual workers.

Recommendation system often suffers from popularity bias. Often the training data inherently exhibits long-tail distribution in item popularity (data bias). Moreover, the recommendation systems could give unfairly higher recommendation scores to popular items even among items a user equally liked, resulting in over-recommendation of popular items (model bias). In this study we propose a novel method to reduce the model bias while maintaining accuracy by directly regularizing the recommendation scores to be equal across items a user preferred. Akin to contrastive learning, we extend the widely used pairwise loss (BPR loss) which maximizes the score differences between preferred and unpreferred items, with a regularization term that minimizes the score differences within preferred and unpreferred items, respectively, thereby achieving both high debias and high accuracy performance with no additional training. To test the effectiveness of the proposed method, we design an experiment using a synthetic dataset which induces model bias with baseline training; we showed applying the proposed method resulted in drastic reduction of model bias while maintaining accuracy. Comprehensive comparison with earlier debias methods showed the proposed method had advantages in terms of computational validity and efficiency. Further empirical experiments utilizing four benchmark datasets and four recommendation models indicated the proposed method showed general improvements over performances of earlier debias methods. We hope that our method could help users enjoy diverse recommendations promoting serendipitous findings. Code available at https://github.com/stillpsy/popbias.

Neural network based models for collaborative filtering have started to gain attention recently. One branch of research is based on using deep generative models to model user preferences where variational autoencoders were shown to produce state-of-the-art results. However, there are some potentially problematic characteristics of the current variational autoencoder for CF. The first is the too simplistic prior that VAEs incorporate for learning the latent representations of user preference. The other is the model's inability to learn deeper representations with more than one hidden layer for each network.