Long-term memory is critical for autonomous Large Language Model (LLM) agents executing multi-session, long-horizon tasks. However, existing memories often inappropriately store, retain, or retrieve over-generalized, misattributed, or privacy-sensitive information, a problem we term memory misalignment. To study this p...
Shu-Ning Zhang, Teng-Hao Ji, Jing-Ruo Chen et al.· 0 citations
Analysing large-scale Chinese-language and English-language social media discourse, this work combines topic clustering with inductive thematic analysis to examine how users interpret the social, moral, and political implications of AI-mediated memory.
Ying Ma, Jarod Govers, Le Fang et al.· 0 citations
A mixed-methods investigation to characterize and mitigate memory misalignment from user perspectives, which highlights the tension between supervisory agency and interaction overhead, and advocates for friction-aware memories that balance user oversight with conversation smoothness.
Jing-Ruo Chen, Shu-Ning Zhang, Er-Yue Xu et al.· 0 citations
Interestingly, greater familiarity within the owner-co-owner dyad was associated with both higher disclosure acceptability and lower co-owner misalignment, whereas the exploratory four-item empathy measure was not.
Han-Xiang Zeng, Shu-Ning Zhang, Xin-Yuan Zhou et al.· 1 citation
AI labels, typically implemented via underlying tracing mechanisms such as watermarks and metadata, are crucial for protecting Artificial Intelligence-Generated Content (AIGC) against security threats like disinformation and evasion. However, the perceived devaluation of AI-assisted work discourages creators from discl...
Shu-Ning Zhang, Hui Wang, Rongjun Ma et al.· 0 citations
AI agents exert substantial social influence comparable in magnitude to that of human peers, and participants reported more dishonestly when exposed to dishonest rather than honest normative cues, highlighting the importance of managing the behaviors and normative signals communicated by AI group members.
Social media fact-checking has long been challenged by evidence-level and aggregation-level conflicts, where erroneous evidence mimics authoritative news sources. To capture this challenge and support conflict verification tasks, we present ContraNote, a large-scale real-world dataset curated from X's Community Notes s...
Shu-Ning Zhang, D. Shi, Bo-Hao Chu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.