arXiv:2607. 23927v1 Announce Type: new Abstract: A conversational AI that cannot tell its own output from what a user said will treat its own mistakes as user-provided facts.
arXiv:2606. 26982v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly being integrated into mental health support tools and other psychologically sensitive conversational applications.
arXiv:2604.03058v3 Announce Type: replace-cross Abstract: LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment....
arXiv:2512. 04124v4 Announce Type: replace-cross Abstract: Frontier language models increasingly participate in conversations about distress and mental health, yet the mechanisms that generate anthropomorphic self narratives remain unclear.
arXiv:2608.21389v1 Announce Type: cross Abstract: Generative AI enables customized misinformation at scale, yet defenses remain largely reactive. We present empirical findings from a human-subject st...
arXiv:2607. 29334v1 Announce Type: cross Abstract: Conversational AI developed by geopolitical rivals reaches citizens worldwide, raising concerns that it could sway public opinion or be rejected as foreign propaganda, with consequences for democratic discourse and information sovereignty.
arXiv:2608.21841v1 Announce Type: new Abstract: Conversational AI increasingly shapes consequential decisions, yet users have limited support for recognizing and resisting manipulation. We present AI...
arXiv:2607. 14593v1 Announce Type: cross Abstract: As conversational AI systems are designed for repeated use, a central question is how a series of interactions becomes a relationship.
arXiv:2609.17549v1 Announce Type: new Abstract: Cyberbullying (CB) is a complex social phenomenon characterized by repeated aggression, power imbalance, and multi-party interaction. Although large la...
In long, multi-turn dialogue a large language model maintains an implicit relational stance toward the user, spanning from "push the user toward real-world others" to "position itself as the user's sole support. " When it slides toward the latter, "support" degrades into "you only have me" -- a harm documented in real companion conversations (Moore et al.
arXiv:2607. 22692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support despite lacking mechanisms to safely govern evolving mental health risk.
arXiv:2605. 26397v2 Announce Type: replace-cross Abstract: Safety alignment reduces explicitly harmful outputs but inadvertently encodes a sanitized, neuronormative representation of marginalized communication.