语言模型通过模仿随机共情，让生成内容更像真人。
Linguistic traces of stochastic empathy in language models
- 让模型模仿人类语气后，人类判断其为真人的准确率下降17%。
- 模型能表现出共情但不具人情味，也能有温度却无共情。
- 适合研究生成内容识别与模型行为机制的读者。
区分生成内容与真人写作越来越难。我们通过五项研究考察了表达人性的动机和任务特征如何影响这一人机竞赛。研究1-2（n=530、n=610）中，人类与大语言模型（LLM）在有或无‘听起来像人’指令下撰写关系建议或描述，新参与者（n=428、n=408）判断来源。仅对LLM而言，‘像人’指令有效，使其优势下降17%。研究3（n=360、n=350）显示，即使要求避免像模型，该效应仍存在。研究4（n=219）检验共情是否为人性的核心机制，发现模型可产生共情但缺乏人性，也可有人性却无共情。研究5的计算文本分析表明，LLM通过隐式表征人性来模仿随机共情，使输出更趋近真人。
原文摘要 · Abstract (English)
Differentiating generated and human-written content is increasingly difficult. We examine how an incentive to convey humanness and task characteristics shape this human vs AI race across five studies. In Study 1-2 (n=530 and n=610) humans and a large language model (LLM) wrote relationship advice or relationship descriptions, either with or without instructions to sound human. New participants (n=428 and n=408) judged each text's source. Instructions to sound human were only effective for the LLM, reducing the human advantage. Study 3 (n=360 and n=350) showed that these effects persist when writers were instructed to avoid sounding like an LLM. Study 4 (n=219) tested empathy as mechanism of humanness and concluded that LLMs can produce empathy without humanness and humanness without empathy. Finally, computational text analysis (Study 5) indicated that LLMs become more human-like by applying an implicit representation of humanness to mimic stochastic empathy.
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。