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:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
By Yoshua Bengio, Oliver Richardson, Tom\'a\v{s} Gaven\v{c}iak, Michael Cohen, Rory Svarc, Damiano Fornasiere, Gael Gendron, David Hyland, Aton Kamanda, Adam Oberman, Francis Rhys Ward, Anna Gaven\v{c}iak, Jacob Livingston Slosser, Vincent Mai, Iulian Serban, Joumana Ghosn
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.
arXiv:2609.14796v1 Announce Type: new
Abstract: The threat that AI persuasion poses to human control has been acknowledged in the literature, but not yet systematically studied. Now that persuasion a...
By Joshua Levy, Mick Yang, Kellin Pelrine
arXiv:2607. 14641v1 Announce Type: new Abstract: Abductive reasoning operates in two directions.
By Remo Pareschi
arXiv:2609.22090v1 Announce Type: new
Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Ps...
By Joy Bose
arXiv:2607. 25166v1 Announce Type: new Abstract: AI chatbots can be ``sycophantic,'' or overly agreeable and flattering toward users.
By Meryl Ye, Robert Kraut, Steve Rathje
arXiv:2610.16946v1 Announce Type: cross
Abstract: Descriptions of how people use AI are becoming training data for the next generation of models. We ask whether what a model reads about its users cha...
By Harsh Kumar, George Eilender, Ashton Anderson
The paper investigates whether AI evaluators differentiate between an argument’s content and the source attributed to it. Using 2,976 evaluations of six fixed texts across various source attributions, the study finds that the perceived quality of an argument varies with its source, indicating source-position coherence. The authors also note that this pattern holds across topics and model configurations, and that some evaluators explicitly noted mismatches between source and position.
arXiv:2507.19364v3 Announce Type: replace
Abstract: The integration of Large Language Models (LLMs) into social simulation has generated considerable enthusiasm, but also raises substantial methodolo...
By Patrick Taillandier, Jean Daniel Zucker, Arnaud Grignard, Benoit Gaudou, Nghi Quang Huynh, Haojia Kong, Alexis Drogoul
arXiv:2607. 15883v1 Announce Type: cross Abstract: Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind.
By Sebastian Cochinescu
The paper investigates a behavioral mechanism for artificial partiality in conversational agents, defining partiality as caring (allocation of surplus interaction above a guaranteed floor) and particularity (per-user state estimates from relationship history). It implements these as a persistence layer over an open-weight base model and evaluates them in constructed multi-session relationships, finding that the mechanism reproduces the ordinal shape of a specified curve but not its magnitude, and that a guarded revision satisfies probe-quality equivalence on a calibrated battery but not on a second battery. The authors note that the mechanism is a candidate for future perception studies rather than evidence that users perceive love, and they outline ethical constraints such as a stranger-treatment floor, bounded surplus, disclosure, and de-intensification.
By Sebastian Cochinescu