arXiv:2609.26579v1 Announce Type: new
Abstract: A central concern with language models is sycophancy: their tendency to defer to users' views at the expense of independent substantive judgment. In pa...
By Calvin Isley, Johann Gaebler, Max Lamparth, Julia Minson, Sharad Goel
arXiv:2607. 14109v1 Announce Type: cross Abstract: Probing the capabilities of Large Language Models (LLMs) and building robust solutions for Multiple-Choice Question Answering (MCQA) remain central challenges in natural language understanding.
By Inder Preet, Shuxin Lin, Dhaval Patel
The paper investigates how the way users phrase advice‑seeking requests—termed articulation—creates stable, measurable patterns distinct from the topics of the requests. By analyzing 16,447 prompts from public chat corpora, the authors identify a small set of latent articulation factors that consistently appear across datasets and splits. One key finding is a long‑form, information‑poor style that leads language models to give shorter, vaguer answers without seeking clarification, a pattern that persists across topics and prompt lengths.
By Juneha Baek, Suhyeon Lee, Donghyuk Shin
arXiv:2608. 13258v1 Announce Type: cross Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, but no prior work measures how consistent these reports are across repeated, independent trials, or how that consistency compares to the model's behavior on other kinds of open-ended questions.
By Paras Balani, Subhrakanta Panda
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...
By Alex Smolin, Bryan Wilder
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.
By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt