arXiv:2609.22090v1 Announce Type: new
Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Ps...
By Joy Bose
arXiv:2609.34284v2 Announce Type: replace
Abstract: Personalized LLMs must decide, for each stored preference, whether the current context calls for applying or suppressing it, which we call its appl...
By Haeun Jang, Yonghyun Jun, Hwanhee Lee
Frontier language models excel at complex tasks yet may prioritize protection over larger physical consequences in simple, urgent decisions. GPT-5.6 Sol, for example, moves a girl playing in shallow w...
The paper investigates how large language model agents that use tools respond to changes in plan priorities versus default plan removal, a phenomenon termed the "default trap." Experiments across 3,200 decision windows on Retail, Airline, and AgentDojo tasks show that switching priorities strongly redirects model choices, while removing a default plan yields weaker responsiveness. Additional studies reveal that the order of account lists and the presence of extra text significantly influence default target selection and priority effects, with overall task success varying from -19.4 to +8.3 points relative to no plan.
By Xueqi Li, Jingjie Ning, Yibo Kong
arXiv:2606. 11016v1 Announce Type: new Abstract: We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic underlying decision structure.
By Gabriel Freedman, Francesca Toni
arXiv:2608. 04735v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models.
By Agatha Duzan, Asa Cooper Stickland
arXiv:2607. 10202v1 Announce Type: new Abstract: Cross-model comparisons read divergence in value dispositions as evidence that language models hold individuated values.
By Hong-In Won, Jinseok Jang, Hyoseop Kim
The paper treats human interventions during LLM agent failures as labels that pinpoint the internal computation that went wrong, rather than merely training data. In a controlled environment, the authors analyze one failure type—over‑asking a clarifying question when the request is already clear—using rule‑based overseer labels validated by blind human judgment. They find that the decision to ask versus act can be causally localized across several models, that over‑asking exhibits distinct mechanistic signatures, and that steering or weight consolidation can mitigate the issue, though outcomes vary by model family.
By Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
arXiv:2609.36614v1 Announce Type: new
Abstract: A commercial incentive need not enter the final ranking algorithm to affect a shopping assistant's recommendation: it may instead influence which prefe...
By Jiapeng Li
A commercial incentive need not enter the final ranking algorithm to affect a shopping assistant's recommendation: it may instead influence which preference question the assistant asks. We make this d...
arXiv:2607. 10251v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in decision support, it is important to understand whether their choices under uncertainty exhibit stable and interpretable behavioural regularities.
By Xuankun Rong, Wenke Huang, Bo Du, Dacheng Tao, Mang Ye
arXiv:2606. 22974v2 Announce Type: replace Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-specific utility structure.
By Yujun Zhou, Christopher M. Ackerman