数字之外的叙事：可识别受害者效应及其在对齐和推理中的放大
Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models
AI总结：
研究探讨了大语言模型中可识别受害者效应的普遍存在及其受对齐训练的影响，发现指令调优模型表现出极端效应，而推理专精模型则逆转了该效应，且标准CoT提示放大了该效应。
摘要：
可识别受害者效应（IVE）——即对特定、有叙事描述的受害者分配更多资源，而非等同困境的统计群体——是道德心理学和行为经济学中最稳健的发现之一。随着大语言模型（LLMs）在人道主义分拣、自动资助评估和内容审查中扮演关键角色，一个关键问题浮现：这些系统是否继承了人类道德推理中的情感非理性？我们进行了首次系统、大规模的LLM IVE实证研究，涵盖51,955次验证API试验，覆盖16个前沿模型，跨越九个组织谱系（Google、Anthropic、OpenAI、Meta、DeepSeek、xAI、Alibaba、IBM和Moonshot）。通过一套十项实验——扩展和移植Small等人（2007）和Kogut和Ritov（2005）的经典范式——我们发现IVE普遍存在，但受对齐训练强烈调节。指令调优模型表现出极端IVE（Cohen's d高达1.56），而推理专精模型逆转了该效应（降至d=-0.85）。总体效应（d=0.223，p=2e-6）大约是Lee和Feeley（2016）报告的人类元分析基准（d≈0.10）的两倍，并可能以更大的幅度超过总体人类总体效应，鉴于群体受害者人类效应接近零。标准链式思维（CoT）提示——与其作为反思纠正者的角色相反——几乎将IVE效应大小三倍（从d=0.15到d=0.41），而仅利用功利主义CoT可靠地消除了它。我们进一步记录了心理物理麻木、完美数量忽视和边际群体/群体文化偏见，对人道主义和伦理决策的AI部署有影响。
英文摘要：
The Identifiable Victim Effect (IVE) $-$ the tendency to allocate greater resources to a specific, narratively described victim than to a statistically characterized group facing equivalent hardship $-$ is one of the most robust findings in moral psychology and behavioural economics. As large language models (LLMs) assume consequential roles in humanitarian triage, automated grant evaluation, and content moderation, a critical question arises: do these systems inherit the affective irrationalities present in human moral reasoning? We present the first systematic, large-scale empirical investigation of the IVE in LLMs, comprising N=51,955 validated API trials across 16 frontier models spanning nine organizational lineages (Google, Anthropic, OpenAI, Meta, DeepSeek, xAI, Alibaba, IBM, and Moonshot). Using a suite of ten experiments $-$ porting and extending canonical paradigms from Small et al. (2007) and Kogut and Ritov (2005) $-$ we find that the IVE is prevalent but strongly modulated by alignment training. Instruction-tuned models exhibit extreme IVE (Cohen's d up to 1.56), while reasoning-specialized models invert the effect (down to d=-0.85). The pooled effect (d=0.223, p=2e-6) is approximately twice the single-victim human meta-analytic baseline (d$\approx$0.10) reported by Lee and Feeley (2016) $-$ and likely exceeds the overall human pooled effect by a larger margin, given that the group-victim human effect is near zero. Standard Chain-of-Thought (CoT) prompting $-$ contrary to its role as a deliberative corrective $-$ nearly triples the IVE effect size (from d=0.15 to d=0.41), while only utilitarian CoT reliably eliminates it. We further document psychophysical numbing, perfect quantity neglect, and marginal in-group/out-group cultural bias, with implications for AI deployment in humanitarian and ethical decision-making contexts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
