提出减少文本生成系统拟人化行为的方法与评估框架
Dehumanizing Machines: Mitigating Anthropomorphic Behaviors in Text Generation Systems
- 通过众包收集用户修改文本以降低拟人化的干预方法
- 构建分类框架，区分不同干预类型及其效果差异
- 为缓解用户过度依赖和情感依附提供理论支持
随着文本生成系统输出越来越具有拟人特征，学者们日益担忧其可能导致用户过度依赖或产生情感依附等有害后果。然而，如何干预系统输出以减轻拟人化行为及其潜在危害，仍缺乏深入研究。本文通过整合文献与众包实验（参与者修改系统输出使其更不具人性），建立干预方法清单，并提出一个概念框架，用于描述干预策略的多样性、区分不同干预类型，并为评估干预有效性提供理论基础。
原文摘要 · Abstract (English)
As text generation systems' outputs are increasingly anthropomorphic -- perceived as human-like -- scholars have also increasingly raised concerns about how such outputs can lead to harmful outcomes, such as users over-relying or developing emotional dependence on these systems. How to intervene on such system outputs to mitigate anthropomorphic behaviors and their attendant harmful outcomes, however, remains understudied. With this work, we aim to provide empirical and theoretical grounding for developing such interventions. To do so, we compile an inventory of interventions grounded both in prior literature and a crowdsourcing study where participants edited system outputs to make them less human-like. Drawing on this inventory, we also develop a conceptual framework to help characterize the landscape of possible interventions, articulate distinctions between different types of interventions, and provide a theoretical basis for evaluating the effectiveness of different interventions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。