AI觉醒星球
Awakening is here
Knowledge File / AI小生意项目库
2026-08-08 0 浏览 会员

读者给AI生成的短篇小说评分高于人类作品,但直到他们得知作者是机器

研究发现,读者无法区分AI和人类写的短篇小说,在不知道作者是AI时甚至给出更高评分;一旦知道是机器所写,评价就会降低。

SOURCE / AI小生意项目库 MIN / 9 ACCESS / 会员 POST / 2026-08-08 22:18:55

原贴

查看原文
作者:Matthias Bastian 来源站点:the-decoder.com 原贴时间:

原文

Readers can't tell the difference between short stories generated by ChatGPT and those written by humans. They even rate the AI-generated texts higher, but only as long as they don't know a machine wrote them. In three experiments with more than 2,500 total participants, test subjects did no better than chance at telling human-written and ChatGPT-generated fictional short stories apart. In the first experiment , each of the 1,682 participants read one of six short stories, each about 1,000 words long. Three came from well-known literary magazines and short story collections. The other three were generated using ChatGPT 4.0, with prompts based on the theme, style, and narrative perspective of the human originals. Half the participants were told the story was written by a human. The other half were told it came from ChatGPT. That information was accurate for only half the participants in each group, according to researchers Sydney Sears and Deena Skolnick Weisberg in their study published in the journal Judgment and Decision Making . ChatGPT's stories were rated significantly higher than the human-written texts on both perceived quality and immersion. For quality, the mean score for AI stories was 1.54 compared to 0.97 for human stories on a scale from minus 3 to plus 3. For immersion, the gap was 1.42 versus 1.00. Participants' own attitudes toward AI also shaped their ratings. Regardless of who actually wrote the story, participants gave higher scores when told a human was the author. Participants with a positive attitude toward AI generally gave higher ratings across the board. When they were also told the story came from ChatGPT, their scores rose even further. Among AI-skeptical participants, this effect flipped. An earlier study on AI-generated poems found a similar bias . In two more experiments with 905 total participants, the researchers made the task harder. Each person read both a human-written and an AI-generated story, then had to figure out which was which. Even with a direct comparison, participants performed no better than chance. Self-reported experience with AI systems correlated positively with the ability to correctly identify the stories' origins. Self-reported experience with fiction, on the other hand, didn't help participants tell them apart. AI-generated texts tend to be smoother, easier to read, and more emotionally upbeat than human-written texts. According to the authors, these traits could explain the higher ratings without the AI stories actually being better in a literary sense. People tend to prefer material that's easier to process. High-quality literary fiction, by contrast, is often intentionally hard to access and pushes readers to work for meaning. A story can be high quality but not very engaging, and vice versa, the researchers suggest. The short story format also likely works in AI's favor. Telling a coherent story in 1,000 words is a very different challenge than doing so across hundreds of pages. Still, the researchers' conclusion is clear: AI can generate creative works people perceive as at least on par with human work, yet people don't believe AI is capable of that.

中文翻译

读者无法区分ChatGPT生成的短篇小说和人类写的短篇小说。他们甚至给AI生成的文本更高评分,但前提是他们不知道是机器写的。在三项实验中,总共有超过2500名参与者,测试对象在区分人类写作和ChatGPT生成的虚构短篇小说方面并不比随机猜测更好。在第一个实验中,1682名参与者每人阅读了六个短篇小说之一,每篇约1000字。三篇来自知名文学杂志和短篇小说集。另外三篇使用ChatGPT 4.0生成,提示基于人类原作的风格、主题和叙事视角。一半参与者被告知故事是人类写的,另一半被告知来自ChatGPT。根据研究员悉尼·西尔斯和迪娜·斯科尔尼克·韦斯伯格发表在《判断与决策》杂志上的研究,这一信息对于每组中只有一半参与者是准确的。ChatGPT的故事在感知质量和沉浸感方面的评分显著高于人类写作的文本。在质量方面,AI故事的平均得分是1.54,而人类故事是0.97,在-3到+3的评分量表上。在沉浸感方面,差距是1.42对1.00。参与者自己对AI的态度也影响了他们的评分。无论故事实际作者是谁,当被告知作者是人类时,参与者给出更高分数。对AI持积极态度的参与者普遍给出更高评分。当他们还被告知故事来自ChatGPT时,分数进一步上升。在怀疑AI的参与者中,这种效应反转了。一项早期关于AI生成诗歌的研究发现了类似的偏见。在另外两个实验中,共905名参与者,研究人员加大了任务难度。每个人阅读人类写作和AI生成的故事,然后必须判断哪个是哪个。即使直接比较,参与者的表现也不比随机好。自我报告的AI系统经验与正确识别故事出处的能力正相关。另一方面,自我报告的小说阅读经验并没有帮助参与者区分它们。AI生成的文本往往比人类写作的文本更流畅、更易读、更情感乐观。作者认为,这些特征可以解释更高的评分,而AI故事在文学意义上并不真的更好。人们倾向于喜欢更容易处理的材料。相比之下,高质量的文学小说常常故意难以理解,迫使读者为了意义而努力。研究人员建议,一个故事可以高质量但不吸引人,反之亦然。短篇小说的形式也可能对AI有利。在1000字内讲一个连贯的故事与在数百页中做到这一点是非常不同的挑战。尽管如此,研究人员的结论是明确的:AI可以生成人们认为至少与人类作品相当甚至更好的创意作品,但人们不相信AI有能力做到这一点。

核心信息

研究发现,读者无法区分AI和人类写的短篇小说,在不知道作者是AI时甚至给出更高评分;一旦知道是机器所写,评价就会降低。

  • 研究发现,读者无法区分AI和人类写的短篇小说,在不知道作者是AI时甚至给出更高评分;一旦知道是机器所写,评价就会降低。
  • 原贴提到:Readers can't tell the difference between short stories generated by Cha
  • 来源:the-decoder.com
试看内容

成为会员查看完整内容

你已经看到了这篇内容的前置整理,剩余深度部分仅对会员开放。

详细解读 信息差价值 参考来源
成为会员查看完整内容
上一篇 OpenAI 意外攻击 Hugging Face 事件时间线现已整理出炉 下一篇 Backflip AI将3D扫描转化为可编辑CAD模型,从数小时缩短至几分钟