arXiv AI
Jun 9
The AI Epistemic Deference Index: A Continuous Measure of Sycophancy
arXiv:2606. 07897v1 Announce Type: new Abstract: Current AI models frequently exhibit epistemic sycophancy, endorsing claims to agree with a user.
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.
Related stories
arXiv AI
Jun 9
"I understand your perspective": LLM Persuasion and Sycophancy through the Lens of Communicative Action Theory
arXiv:2606. 08076v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored.
arXiv AI
Jun 6
A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing
arXiv:2606. 05330v1 Announce Type: cross Abstract: Large language models can shift human beliefs across high-stakes domains, but most persuasion studies rely on pre/post belief change.
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 AI
Jul 22
"I understand your perspective": LLM Persuasion through the Lens of Communicative Action Theory
arXiv:2606. 08076v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored.
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
6d ago
Social Meaning in Large Language Models: Structure, Magnitude, and Pragmatic Prompting
arXiv:2604. 02512v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly exhibit human-like patterns of pragmatic and social reasoning.
arXiv AI
Jun 26
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.
arXiv AI
Jul 31
Ask don't tell: Reducing sycophancy in large language models
arXiv:2602. 23971v4 Announce Type: replace-cross Abstract: Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts.
arXiv AI
Jun 8
Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns
arXiv:2601. 05751v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for everyday communication tasks, including drafting interpersonal messages intended to influence and persuade.
arXiv AI
Jun 9
From `May' to `Is': Certainty Distortion in Language Model Rewriting
arXiv:2606. 07951v1 Announce Type: cross Abstract: Humans increasingly turn to Language Models (LMs) in ways that shape beliefs and drive decisions, including discussing, rewriting, and summarizing information from scientific articles, news, and medical reports.
Hugging Face Trending Papers
Jun 11
Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday Reasoning
When large language models (LLMs) fail to generalize or make haphazard errors in reasoning, it is often taken as evidence that LLMs are not truly reasoning, but rather performing a kind of pattern matching. The implication is that people's behavior does not exhibit the same types of failures because human reasoning uses principled and abstract world models.