arXiv AI

Persona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation

Persona prompting is widely used in LLM user simulation, yet it assumes that specifying a target user attribute will shift only that attribute while leaving others unchanged. Across multiple models, the study finds that changing a target attribute also alters unspecified non‑target choices, creating a "neutrality gap" that persists even when no preference is declared. The authors show that blocking query‑time attention reduces non‑target drift, but this also weakens target efficacy, highlighting a central challenge in achieving selective control.

arXiv AI
Sep 30

The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents

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 AI
Jun 10

Superficial Beliefs in LLM Decision-Making

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 AI
Oct 16

Human Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures

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