11-19 更新 实时
首页/ 算力/ 正文

有性格的聊天机器人?AI 如何描述自己并评判我们

算力 来源:TechXplore 2026-11-05 05:40 0 阅读 机器翻译
有性格的聊天机器人?AI 如何描述自己并评判我们

由 Lisa Lock 编辑,Robert Egan 审阅

本文已按照 Science X 的编辑流程与政策进行审阅。编辑在确保内容可信度的同时,重点标注了以下属性:

同行评审出版物

添加到首选来源

大型语言模型(即 AI 驱动的聊天机器人)生成的文本会表现出特征性的“人格”特质。这类聊天机器人也能识别文本中个体的人格特质。不过,据美因茨约翰内斯·古腾堡大学(JGU)心理学研究所的研究人员称,在区分人类撰写与 AI 生成的文本方面,人类更为可靠。

“聊天机器人正越来越多地融入我们生活的各个领域,从客户服务和数字咨询服务,到许多人日常已在使用的个人聊天机器人——人们甚至会向它们倾诉自己的感受,”JGU 人格心理学与心理评估系研究员、发表于 Scientific Reports 的该研究第一作者 Sophie Körner 表示。“正因如此,我们需要了解我们如何感知聊天机器人生成的文本,以及我们是否还能将它们与人类撰写的文本区分开来。”

比人类更尽责、更随和、情绪更稳定

在这项研究中,Körner 与 Sarah Osterholz 博士和 Boris Egloff 教授一起,将 7 个 AI 语言模型——ChatGPT-4o、ChatGPT-3.5、Llama-3、Gemma 2、Gemini 2.5、Phi-3 和 Orca 2——的自我描述与 70 名人类的自我描述进行了比较。他们借助心理问卷和开放式问题,要求聊天机器人和人类参与者用德语描述各自“的人格”。

例如,他们被要求对有关自身自尊以及大五人格特质(如开放性、宜人性和外向性)的陈述进行评分。随后的开放式问题聚焦于他们的兴趣、对未来的期望,以及在压力情境下的典型行为。每个语言模型都被询问 10 次,研究人员共获得 140 份文本用于分析。

研究团队首先考察了这些语言模型在被反复询问时回答的相似程度。“我们的结果表明,语言模型确实会随着时间推移为自身赋予相当稳定的人格画像,”合著者 Osterholz 表示。与人类参与者相比,语言模型呈现出的自我形象更尽责、更宜人、情绪也更稳定。

人类在识别 AI 生成文本方面更可靠

接下来,研究人员请 10 名人类和 6 个聊天机器人来评估这些自我描述。他们需要根据文本评估开放性、尽责性和自尊等人格特质。人类和聊天机器人都能就人格特质得出结论。不过,聊天机器人对人类作者某些特质的评分(包括开放性和自尊)往往高于人类评分者。反过来,在所有被考察的特质上,人类评分者对语言模型的打分往往高于人类撰写的文本,尤其是情绪稳定性。

评分者还被要求判断每段文本是由人类还是 AI 模型撰写的。人类评分者的准确率达到 83%,而聊天机器人仅为 67%。在这项任务中表现最好的两个 AI 模型 Gemma 和 Gemini,在判断文本由人类还是 AI 撰写方面,可靠程度与普通人类评分者大致相当。

两组都倾向于更频繁地把文本归类为人类所写,可能是为了避免把人类撰写的文本误判为 AI 所写。具体而言,聊天机器人生成的文本被错误归类为人类所写的可能性,要高于把人类文本误判为 AI 生成的反向情况。不过,随着 AI 模型的训练数据越来越多地包含 AI 生成的文本,它们在识别一段文本由人类还是 AI 撰写方面可能会变得准确得多。

人类评分者主要将 AI 生成文本的长度,以及其生硬、尤其偏技术或分析性的语言,列为区分特征。一项计算机辅助的语言学分析也揭示了差异:AI 生成的文本包含更多与时间相关的表达,以及冠词、介词等功能词,而人类的自我描述则更多聚焦于休闲活动、情感和社会关系。

在心理评估中的潜在应用

据研究人员称,AI 语言模型未来也可用于心理评估和人力资源领域,例如初步了解人格特质。一些职场环境已经在推进此类应用。然而,这些方法的可靠性如何、以及在什么条件下可以使用,目前仍不清楚。

“它们可以提供一种自动化、易于获取的初步评估,”Körner 说。但由于语言模型是在人类撰写的文本上训练的,它们也会习得偏见,也就是判断上的偏差。因此,重要的是要仔细审视,尤其从伦理角度出发,敏感领域的人格评估是否应该交给算法。

Sophie T. Koerner 等,《大语言模型与人类中的性格表达与感知》,Scientific Reports(2026)。DOI: 10.1038/s41598-026-75546-5

期刊信息:Scientific Reports

这篇报道由谁撰写?

艺术史学士,物质文化硕士。曾任博物馆编辑、急救员和器官移植协调员。自 2021 年起在 Science X 担任编辑。完整简介 →

数学生物学学士,创意写作硕士。游历广泛,对科学与语言有独到见解。完整简介 →

引用:有性格的聊天机器人?AI 如何描述自己并评判我们(2026 年 11 月 4 日),2026 年 11 月 6 日检索自 https://techxplore.com/news/2026-11-chatbots-personality-ai.html

本文档受版权保护。除为私人学习或研究目的进行的合理使用外,未经书面许可不得复制任何部分。内容仅供参考。

获取即时摘要文本(Gist)

七种语言模型给出了前后一致的自我描述,其展现出的尽责性、宜人性和情绪稳定性均高于人类。人类和聊天机器人都能从文本中推断人格特质,但人类识别文本作者身份的准确率更高(83% 对 67%)。可靠性和偏见仍是自动化人格评估面临的隐忧。

本摘要由 LLM 自动生成。完整免责声明

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(Chatbots with personality? How AI describes itself and judges us)

Chatbots with personality? How AI describes itself and judges us

Chatbots with personality? How AI describes itself and judges us

edited by Lisa Lock, reviewed by Robert Egan

This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

peer-reviewed publication

Add to Preferred Sources

chatbot Credit: Pixabay/CC0 Public Domain

Texts generated by large language models, or AI-powered chatbots, exhibit characteristic "personality" traits. Such chatbots can also identify individual personality traits in texts. However, humans are more reliable at distinguishing between human-written and AI-generated texts, according to researchers at the Institute of Psychology at Johannes Gutenberg University Mainz (JGU).

"Chatbots are becoming part of more and more areas of our lives, from customer service and digital counseling services to personal chatbots that many people already use every day and even share their feelings with," said Sophie Körner, a research associate in the Department of Personality Psychology and Psychological Assessment at JGU and lead author of the study published in Scientific Reports. "That is why we need to understand how we perceive chatbot-generated texts and whether we can still distinguish them from human-written texts."

More conscientious, agreeable and emotionally stable than humans

For their study, Körner, together with Dr. Sarah Osterholz and professor Boris Egloff, compared the self-descriptions of seven AI language models—ChatGPT-4o, ChatGPT-3.5, Llama-3, Gemma 2, Gemini 2.5, Phi-3 and Orca 2—with those of 70 humans. Using psychological questionnaires and open-ended questions, they asked the chatbots and human participants to describe their respective "personalities" in German.

For example, they were asked to rate statements about their self-esteem and the Big Five personality traits, such as openness, agreeableness and extraversion. The subsequent open-ended questions focused on their interests, hopes for the future and typical behavior in stressful situations. Each language model was questioned 10 times, giving the researchers a total of 140 texts to analyze.

The team first examined how similar the language models' responses were when questioned repeatedly. "Our results show that the language models do indeed attribute fairly stable personality profiles to themselves over time," said co-author Osterholz. Compared with the human participants, the language models presented themselves as more conscientious, agreeable and emotionally stable.

Humans are more reliable at identifying AI-generated texts

Next, the researchers asked 10 humans and six chatbots to evaluate the self-descriptions. Based on the texts, they were asked to assess personality traits such as openness, conscientiousness and self-esteem. Both humans and chatbots were able to draw conclusions about personality traits. However, the chatbots tended to rate some traits of the human authors, including openness and self-esteem, higher than the human raters did. Conversely, the human raters tended to assign higher scores to the language models than to the human-written texts for all traits examined, particularly emotional stability.

The raters were also asked to determine whether each text had been written by a human or an AI model. The human raters achieved an accuracy of 83%, compared with just 67% for the chatbots. The two best-performing AI models in this task, Gemma and Gemini, were about as reliable as the average human rater at identifying whether a text was written by a human or AI.

Both groups tended to classify texts as human-written more often, possibly to avoid misattributing human-written texts to AI. Specifically, chatbot-generated texts were more likely to be incorrectly classified as human-written than vice versa. However, AI models may become significantly more accurate at identifying whether a text was written by a human or AI as their training data increasingly include AI-generated texts.

The human raters primarily cited the length of AI-generated texts and their stilted, particularly technical or analytical language as distinguishing features. A computer-assisted linguistic analysis also revealed differences: AI-generated texts contained more time-related expressions and function words such as articles and prepositions, while human self-descriptions more often focused on leisure activities, feelings and social relationships.

Potential applications in psychological assessment

According to the researchers, AI language models could also be used in psychological assessment and human resources in the future, for example, to obtain an initial picture of personality traits. Such applications are already being pursued in some workplace settings. However, it remains unclear how reliable these methods are and under what conditions they could be used.

"They could provide an automated, easily accessible initial assessment," said Körner. But since language models are trained on human-written texts, they also acquire biases, meaning distortions in judgment. It is therefore important to carefully examine whether personality assessments in sensitive areas should be left to algorithms, particularly from an ethical perspective.

Sophie T. Koerner et al., Personality expression and perception in large language models and humans, Scientific Reports (2026). DOI: 10.1038/s41598-026-75546-5

Journal information:Scientific Reports

Who's behind this story?

Lisa Lock

BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile →

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →

Citation: Chatbots with personality? How AI describes itself and judges us (2026, November 4) retrieved 6 November 2026 from https://techxplore.com/news/2026-11-chatbots-personality-ai.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

Get Instant Summarized Text (Gist)

Seven language models gave consistent self-descriptions portraying greater conscientiousness, agreeableness and emotional stability than humans. Both humans and chatbots inferred personality traits from texts, but humans identified text authorship more accurately (83% versus 67%). Reliability and bias remain concerns for automated personality assessment.

This summary was automatically generated using LLM. Full disclaimer

This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use.

原文为英文,正文由自动抓取并保留原文。

本文由采集器自动同步

原文发布于 TechXplore(Chatbots with personality? How AI describes itself and judges us),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗