Preference-driven behavior in LLMs may be a necessary precondition for AI misalignment such as sandbagging: models cannot strategically pursue misaligned goals unless their behavior is influenced by their preferences. Yet prior work has typically prompted models explicitly to act in specific ways, leaving unclear whether observed behaviors reflect instruction-following capabilities vs underlying model preferences. Here we test whether this precondition for misalignment is present. Using entity preferences as a behavioral probe, we measure whether stated preferences predict downstream behavior in five frontier LLMs across three domains: donation advice, refusal behavior, and task performance. Conceptually replicating prior work, we first confirm that all five models show highly consistent preferences across two independent measurement methods. We then test behavioral consequences in a simulated user environment. We find that all five models give preference-aligned donation advice. All five models also show preference-correlated refusal patterns when asked to recommend donations, refusing more often for less-preferred entities. All preference-related behaviors that we observe here emerge without instructions to act on preferences. Results for task performance are mixed: on a question-answering benchmark (BoolQ), two models show small but significant accuracy differences favoring preferred entities; one model shows the opposite pattern; and two models show no significant relationship. On complex agentic tasks, we find no evidence of preference-driven performance differences. While LLMs have consistent preferences that reliably predict advice-giving behavior, these preferences do not consistently translate into downstream task performance.
Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
University of Chinese Academy of Sciences(中国科学院大学);Chinese Information Processing Laboratory(中文信息处理实验室);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)
CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations
Department of Computer Science (DIKU), University of Copenhagen(哥本哈根大学计算机科学系(DIKU));Centre for Language Technology (CST), University of Copenhagen(哥本哈根大学语言技术中心);Pioneer Centre for Artificial Intelligence(先锋人工智能中心)
ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系);Singapore-MIT Alliance for Research and Technology Centre(新加坡-麻省理工联盟研究技术中心);The Chinese University of Hong Kong, Shenzhen, China(香港中文大学(深圳));CSAIL, Massachusetts Institute of Technology(麻省理工学院计算机科学与人工智能实验室);Institute of Data Science, National University of Singapore(新加坡国立大学数据科学研究院)
Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Models
School of Computer Science and Technology, Beijing Jiaotong University(北京交通大学计算机与信息技术学院);Beijing Key Laboratory of Traffic Data Analysis and Mining(北京市交通数据分析与挖掘重点实验室);Department of Computer Science, Aalborg University(奥尔堡大学计算机系)
Aligning Language Model Benchmarks with Pairwise Preferences
School of Data Science, University of Virginia(弗吉尼亚大学数据科学学院);Imperial College London(伦敦帝国理工学院);Thomson Reuters Foundational Research(汤姆森路透基础研究);Department of Electrical Engineering and Computer Science, UC Berkeley and UCSF(伯克利大学电气工程与计算机科学系及旧金山大学)