arXiv AI
Jun 11
When Roleplaying, Do Models Believe What They Say?
arXiv:2606. 11502v1 Announce Type: cross Abstract: Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite.
When Role-playing, Do Models Believe What They Say?
arXiv:2606. 11502v3 Announce Type: replace-cross Abstract: Language models can state that "the Earth orbits the Sun" and, when role-playing Aristotle, assert the opposite.
Related stories
arXiv AI
Jul 28
Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas
arXiv:2605. 09159v2 Announce Type: replace Abstract: Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors".
Hugging Face Trending Papers
Jul 8
Dissociating the Internal Representations of Sycophancy in LLMs
Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect. While sycophancy is often treated as a single defined behavior, it can manifest in substantially distinct ways and circumstances, raising the question of whether this multi-faceted nature is reflected in its internal mechanisms.
arXiv Machine Learning
Jul 9
Dissociating the Internal Representations of Sycophancy in LLMs
arXiv:2607. 07003v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit sycophancy, where they agree with a user's statement even when incorrect.
arXiv AI
Jun 9
Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy
arXiv:2605. 21006v2 Announce Type: replace Abstract: We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect.
Hugging Face Trending Papers
Jun 30
Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
Theory of Mind (ToM) benchmarks for Large Language Models (LLMs) typically rely on passive question-answering formats, but the deployment of LLMs in increasingly agentic and autonomous forms demands new evaluations. In this paper we evaluate an agent's ability to induce specific belief states in other agents by taking actions rather than using conversational persuasion, a capability we call Non-Conversational Planning ToM (NCP-ToM).
arXiv AI
Jul 10
Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring
arXiv:2604. 07102v2 Announce Type: replace-cross Abstract: Activation-based steering enables inference-time personalization of large language models, but its effects in educational applications are not well understood.
arXiv AI
Jun 30
Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects
arXiv:2603. 03915v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have shown remarkable potential in developing role-playing agents (RPAs).
arXiv AI
Jul 29
Evaluating Communicative Belief Updates in Large Language Models via Implicature Recognition and Cancellation
arXiv:2607. 25094v1 Announce Type: cross Abstract: Human language is driven by unspoken beliefs and belief updates, making these critical to model for successful communication between large language models (LLMs) and their users.
arXiv AI
Jul 24
The Storyteller in the Model: Narrative Pattern Inheritance, Escalation Dynamics, and Alignment Governance in LLMs
arXiv:2607. 20449v1 Announce Type: cross Abstract: LLMs are trained predominantly on human-authored text, yet the structural and narrative conventions embedded in that text are rarely examined as a source of systematic behavioral influence, or as a governance risk in deployed systems.
arXiv AI
Jul 20
Verbalizable Representations Form a Global Workspace in Language Models
arXiv:2607. 15495v1 Announce Type: cross Abstract: Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning.
arXiv AI
Jul 20
Perceived AGI: Believability as Dimensional Completeness, Not Capability
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.