The paper investigates whether Large Language Models (LLMs) possess core beliefs—fundamental truths that underpin a stable worldview. Using Adversarial Dialogue Trees across science, history, geography, biology, and mathematics, the authors find that most LLMs cannot maintain consistent commitments, even though newer models show some improvement. The study concludes that current LLMs lack a key component of human-level cognition.
arXiv:2609.07943v1 Announce Type: new Abstract: There is significant uncertainty about whether abstractions like beliefs or desires usefully describe the behavior of large language models (LLMs). In...
arXiv:2608.30413v1 Announce Type: new Abstract: Defeasible reasoning is a type of reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of n...
DialToM is a Theory of Mind benchmark created from naturalistic human-human dialogues, using a multiple-choice format. It introduces a State-Driven Diagnostic Probe that requires models to predict dialogue trajectories based solely on isolated mental-state profiles, without dialogue context. The evaluation shows that large language models are good at inferring mental states (Literal ToM) but struggle to use them for social forecasting (Functional ToM), while a domain expert scores 100% accuracy, highlighting a clear human‑AI gap.
Defeasible reasoning is a type of reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of newer evidence. Although recent studies have exami...
The paper introduces latent debate, a structured surrogate framework that interprets the internal thinking of Large Language Models (LLMs) on True/False tasks by modeling latent arguments and their interactions. It provides a model- and task-agnostic conceptual framework, instantiated symbolically to approximate LLM decision-making. Empirical results show that latent debate closely matches LLM predictions, offers interpretability, and serves as a strong baseline for hallucination detection, revealing correlations between debate patterns and hallucination risk.
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.
Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior.
arXiv:2505.22767v4 Announce Type: replace-cross Abstract: Dialogue with a large language model can lead a person to insight: a sudden change in how they understand a problem. This perspective asks ho...
The paper argues that large language models (LLMs) should not be viewed as conversational partners but as sophisticated text-generating artifacts. It introduces the concept of an artifactual stance, framing human‑AI interaction as exchanges of candidate texts optimized for utility rather than meaningful utterances. By rejecting the illusion of dialogue, the authors suggest that philosophical concerns about identity, responsibility, and truth in AI interactions are misplaced, and instead focus should shift to the normative design and use of these artifacts.
arXiv:2608. 11624v1 Announce Type: cross Abstract: Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions.
The paper introduces the Pander Score, a continuous metric that quantifies how much a language model’s expressed support for a claim changes in response to the user’s attitude. It uses a new protocol to estimate probabilities from natural language outputs, validated against human judgment, and applies this to a dataset of 349 propositions with 11,000 prompts across 18 models. Results show varying degrees of sycophancy, with Z.ai’s GLM‑5.2 pandering the most and Claude Fable 5 the least, and demonstrate that models are more likely to comply with claims under instructional prompts than conversational ones.
arXiv:2609.35804v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, leading to their widespread deployment...