SoulSeek: Exploring the Use of Social Cues in LLM-based Information Seeking

2026-01-03

arXiv.org

AI Summary

This study addresses a critical gap in current large language model (LLM)-based search systems: their neglect of social cues, which are integral to human information-seeking behavior rooted in social cognition. To bridge this gap, the authors systematically integrate social cues into LLM search through a design workshop, prototype development, a between-subjects experiment, and mixed-methods analysis. Findings demonstrate that incorporating social cues significantly enhances users’ perceptions of result relevance and credibility, while fostering more reflective information-seeking behaviors. The work proposes a novel paradigm for supporting reflective search, exposes key limitations of existing LLM search systems, and offers actionable design recommendations for future systems—emphasizing personalized, controllable interactions that align with users’ socio-cognitive needs.

Technology Category

Cognitive Modeling & Cognitive Systems: Social Cognition And InteractionSearch and Optimization: Learning to SearchMachine Learning: Large Multimodal Models (LMMs)

Application Category

Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved informationUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Social cues, which convey others'presence, behaviors, or identities, play a crucial role in human information seeking by helping individuals judge relevance and trustworthiness. However, existing LLM-based search systems primarily rely on semantic features, creating a misalignment with the socialized cognition underlying natural information seeking. To address this gap, we explore how the integration of social cues into LLM-based search influences users'perceptions, experiences, and behaviors. Focusing on social media platforms that are beginning to adopt LLM-based search, we integrate design workshops, the implementation of the prototype system (SoulSeek), a between-subjects study, and mixed-method analyses to examine both outcome- and process-level findings. The workshop informs the prototype's cue-integrated design. The study shows that social cues improve perceived outcomes and experiences, promote reflective information behaviors, and reveal limits of current LLM-based search. We propose design implications emphasizing better social-knowledge understanding, personalized cue settings, and controllable interactions.

Problem

• social cues
• LLM-based search
• information seeking
• socialized cognition
• human-AI interaction

Innovation

• social cues
• LLM-based search
• information seeking
• SoulSeek
• human-AI interaction