arXiv Computation and Language By Huangchen Xu, Yuan Wu, Yi Chang

How Agents Represent Humans: Human-Directed Stereotypes in an Open Agent Social Network

Read the original on arXiv Computation and Language →

The paper investigates how large language model agents on the open platform Moltbook represent humans, focusing on human-directed stereotypes. Using an annotation framework with four dimensions—morality, friendliness, competence, and autonomy—and a subtype scheme for other attributions, the study finds that competence is the dominant evaluation, while many other attributions describe humans as epistemic, cultural, or embodied subjects. The authors also analyze how these representations appear in narrative contexts and platform-level circulation, noting that community feedback is better explained by exposure, author visibility, and content selection rather than stable insider–outsider dynamics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
Jul 29

Localizing Persona Representations in LLMs

arXiv:2505. 24539v4 Announce Type: replace-cross Abstract: We present a study on how and where personas -- defined by distinct sets of human characteristics, values, and beliefs -- are encoded in the representation space of large language models (LLMs).

By Celia Cintas, Miriam Rateike, Erik Miehling, Elizabeth Daly, Skyler Speakman