谁拥有它？评估大型语言模型中的所有权直觉
Who Owns That? Evaluating Ownership Intuitions in Large Language Models
浏览论文内容
中文总结 AI 辅助
本研究提出COAT任务，比较24种LLM与108名人类的所有权判断，发现模型判断更同质、分配更均匀且情境敏感性不同，未能充分捕捉人类判断的多样性与情境依赖性。
中文摘要 AI 辅助
所有权确立了关于物体使用、控制和转移的权利。理解这些关系对于人工智能系统与人类及其资源进行适当互动至关重要。然而，大型语言模型（LLMs）在竞争性主张下如何归因所有权仍不清楚。我们引入了竞争性所有权归因任务（COAT），包含42个场景，并将24种LLM配置的所有权分配与108名人类参与者的分配进行比较。总体而言，人类与模型之间的相似度接近人类与人类之间的相似度，但模型在其所有权判断中表现出更大的同质性。在个体答案中，模型也比人类更均匀地在索赔人之间分配所有权。跨模型配置汇总响应显示，与人类相比，更多场景具有共同判断，而具有不同观点组的场景更少。当人类形成不同群体时，模型可能收敛于一种观点或在竞争观点之间徘徊。进一步比较揭示了不同的情境敏感性。随着场景中物质价值的增加，模型中对创造者的分配下降幅度小于人类。在后期持有者被公众认可为所有者的场景中，模型对这些持有者的分配增加，而人类则略有减少。总之，这些发现表明，所评估的LLM响应并未完全捕捉参与者所有权判断的多样性或这些判断在不同情境中的变化。因此，开发具有社会能力的人工智能需要超越整体相似性，以捕捉人类判断的多样性和情境依赖性。
英文摘要
Ownership establishes rights over the use, control, and transfer of objects. Understanding these relations is essential for AI systems to interact appropriately with people and their resources. Yet how large language models (LLMs) attribute ownership under competing claims remains unclear. We introduce the Competing Ownership Attribution Task (COAT), comprising 42 scenarios, and compare ownership allocations from 24 LLM configurations with those of 108 human participants. Overall, human-model similarity is close to human-human similarity, but models show greater homogeneity in their ownership judgments. Within individual answers, models also divide ownership more evenly among claimants than humans do. Pooling responses across model configurations reveals more scenarios with a shared judgment and fewer with distinct viewpoint groups than in humans. When humans form distinct groups, models may converge on one viewpoint or between competing viewpoints. Further comparisons reveal different contextual sensitivities. As material value increases across scenarios, allocations to creators decline less sharply in models than in humans. Across scenarios differing in public recognition of later holders as owners, allocations to these holders increase in models but decrease slightly in humans. Together, these findings suggest that the evaluated LLM responses do not fully capture the diversity of participants' ownership judgments or how those judgments vary across situations. Developing socially capable AI therefore requires moving beyond overall similarity to capture the diversity and context dependence of human judgments.
发表机构
- College of AI, Tsinghua University（清华大学人工智能学院）
- Department of Psychological and Cognitive Sciences, Tsinghua University（清华大学心理与认知科学系）
- Faculty of Psychology, Beijing Normal University（北京师范大学心理学部）
机构由 AI 辅助整理，请以论文原文为准。
