能辨“单次—多次博弈”的大语言模型：理解与干预风险决策
Large language models capable of distinguishing between single and repeated gambles: Understanding and intervening in risky choice
风险决策的理论研究主要依赖行为结果的逆向推理和自我报告数据，缺乏对决策过程的直接观测，制约了其内在机制解释及有效行为干预方案开发。人工智能大语言模型(LLMs)的运用为克服以上局限提供了途径。本文通过三项研究系统考察了LLMs在风险决策中的模拟潜力，基于DeepSeek-R1进行单次和多次博弈并生成决策依据，并运用GPT-4o对其进行归纳性主题分析(ITA)，构建了LLMs生成决策策略文本的技术路径，并将其用于决策干预。发现：(1) ChatGPT-3.5/4能复现人类单次(更风险规避)与多次(更风险寻求)博弈的典型选择模式；(2) LLMs能分清单次/多次博弈逻辑，并正确分别运用规范性和描述性理论生成相应策略，其策略被认可度高；(3) LLMs基于不同策略生成的干预文本能有效影响人们在医疗、金融、内容创作和电商营销情境中固有的风险决策偏好。研究系统验证LLMs对行为偏好的模拟能力，对决策的理解力，并构建了基于生成式AI的决策干预新范式，为人工智能辅助高风险决策提供了理论和实践基础。
信息传播、知识传播科学、科学研究计算技术、计算机技术
风险决策单次/多次博弈大语言模型决策策略干预
周蕾,李立统,王旭,区桦烽,胡倩瑜,李爱梅,古晨妍.能辨“单次—多次博弈”的大语言模型：理解与干预风险决策[EB/OL].(2025-11-02)[2025-11-07].https://chinaxiv.org/abs/202509.00060.点此复制
Risky choice (RC) is a common and important form of decision making in daily life. Its theoretical development primarily follows two major theories: normative theory and deThis work comprises three studies. In Study 1, GPT-3.5 and GPT-4 were employed to simulate human responses to gambling decisions under nine probability conditions (with constant expected value), which generated a total of 3,600 responses across single and repeated gamble scenarios. In Study 2, LLM-generated strategies were constructed through a three-stage process (decision rationale extraction, strategy generation and quality evaluation), then the human participants were required to complete decision-making tasks in two experiments: Experiment 1 replicated the medical/financial scenarios (N = 349, N male = 174, M age = 21.79) of Sun et al. (2014) in a 2 (context: medical vs. financial) 2 (application frequency: single vs. repeated) within-subjects design, and Experiment 2 examined digital contexts with a 2 (context: content creation vs. e-commerce marketing) 2 (frequency: single vs. repeated) mixed design (context as between subjects). Subsequently, DeepSeek-R1 was used to perform the same tasks and generate strategy texts through the three-stage process. Finally, the participants were instructed to evaluate their acceptance of the LLM-generated strategies. Study 3 extended the Study 2 methodology to determine whether the LLM-generated intervention texts could reverse the participants classic choice preference across the single versus repeated gamble scenarios. The Study 2 experimental contexts (Experiment 1: medical vs. financial, N = 460, N male = 205, M age = 21.80; Experiment 2: content creation vs. e-commerce marketing, N = 240, N male = 106, M age = 29.12) were mirrored in Study 3, in which strategically designed intervention texts were presented during the decision-making tasks to test their capacity to modify the participants inherent risk preference between the single and repeated gamble conditions and evaluate the persuasive efficacy of LLM-generated strategies on human decision biases.Study 1 shows that the LLMs (GPT-3.5 and GPT-4) can successfully replicate the typical human pattern of risk aversion in single-play scenarios and risk seeking in repeated-play scenarios, though both models demonstrated an overall stronger tendency toward risk seeking compared with the human participants. Study 2 demonstrates that the human participants preferred low-EV certain options in single-play contexts and high-EV risky options in repeated-play contexts in both experiments. The participants also showed high agreement with the strategies generated by the LLMs in different scenarios. Study 3 confirms that the LLM-generated intervention texts can significantly influence the participants choice tendency in all four scenarios, with strong intervention effects observed in the single-play contexts. The LLM intervention strategies are characterised by reliance on expected value computations (normative) when promoting RCs and emphasis on certainty and robustness (deIn summary, this study demonstrates that (1) LLMs can effectively simulate context-dependent human preferences in RC, particularly the shift from risk aversion in single plays to risk seeking in repeated plays; (2) LLMs can distinguish between the logic underlying single and repeated gambles and apply normative and descriptive reasoning accordingly to externalise decision strategies; and (3) the decision strategies extracted from LLM-generated reasoning can be used to construct effective intervention texts that can alter human preferences in classic risk decision tasks, thereby validating the feasibility and effectiveness of an LLM-based cognitive intervention pathway. This study offers a new technological paradigm for AI-assisted decision intervention and expands the application boundary of LLMs to human cognitive process modelling and regulation.
risk decision-makingsingle- vs. repeated-play gambleslarge language modelsdecision strategyintervention
展开英文信息
评论