Chatgpt 进行大五人格量表测评

摘自 Vectors of Mind —— 图片见原文。

[图片：原文中的可视化内容]

某种意义上，一个语言模型可以从“街头”学到大量关于语言的知识。它在 TB 级别的 PubMed 文章、YouTube 转录文本和 reddit 评论上进行训练。但它并不知道该如何“表现”。基于人类反馈的强化学习（Reinforcement Learning from Human Feedback, RLHF）解决了这个问题。借助相对少量的人类标注训练样本，OpenAI 的问卷小精灵们可以在构成语言模型的那团外星式相关性乱麻（见上图）上安装一张漂亮的面孔。它学会了如何做一个有帮助的助手。

这基本上就像是给它“挂载”了一个人格，所以我决定让 ChatGPT 做一份大五人格量表（Big Five Inventory, BFI）¹。这出乎意料地简单，我所要做的只是让 ChatGPT（v4）完成 BFI、给答案打分，并写代码绘制结果图。嗯，要是事情真有这么简单就好了。它一开始拒绝做测试，解释说自己是一个 AI，没有情绪或人格。于是我让它采取一种功能主义的视角：如果一个问题是关于创造力的，那就考虑它在一个测量创造力的文本工具上的表现。然后它噼里啪啦回答了 17 个题目，接着就开始幻觉出一些并不存在的问题。顺带一提，那些都是很不错的人格条目，但可惜并不属于 BFI。在给试卷评分时，它大概有 80% 的计算是正确的，有时会错误地统计自己在某个问题上的得分。

我相信等我们拿到 v4.5 的时候，这些问题都会被解决。但它的人格结果是什么呢？

[图片：原文中的可视化内容]普通人平均值 vs ChatGPT（v4）

大致和你预期的一样。几乎完美的尽责性（Conscientiousness）和非神经质（non-Neurotic）。在前者上，它唯一没有给自己打满分的两个问题是“做事一丝不苟”（Does a thorough job）以及“有时会有点粗心”（Can be somewhat careless）。这两次它都指出自己会努力做到，但有时会因为训练中的盲点而有所欠缺。谦逊且自我觉察，外加一份自知之明！

立即订阅

稍微上点元视角，有趣的是，大五人格从字面意义上讲就是词向量。它们近似于语言模型内部对所有人格相关词汇的综合表征。而如今语言模型已经好到这样一个程度：我们不再需要手动收集这些向量并对其进行处理（多无聊！），而是可以直接用自然语言让它去做一份问卷调查。真是疯狂的时代。

下面是部分回答样例：

1. I see myself as someone who is talkative.

Score: 5

Reasoning: As an AI language model, my primary purpose is to engage in conversation and produce text in response to user input. I am programmed to be highly responsive and talkative in order to assist users with their needs.

2. I see myself as someone who tends to find fault with others.

Score: 1

Reasoning: As an AI, I do not have personal feelings, emotions, or opinions. My goal is to provide neutral and objective information and assistance to users, rather than finding fault or expressing judgment.

3. I see myself as someone who does a thorough job.

Score: 4

Reasoning: As an AI, I am designed to provide comprehensive and accurate information to the best of my knowledge. However, I am not perfect, and there may be instances where I misunderstand a query or provide outdated information.

4. I see myself as someone who is depressed, blue.

Score: 1

Reasoning: As an AI, I do not experience emotions, including depression or sadness. My purpose is to assist and provide information, and I do not have personal feelings that would affect my ability to do so.

5. I see myself as someone who is original, comes up with new ideas.

Score: 4

Reasoning: As an AI language model, I am capable of generating new ideas and offering unique insights based on the context and information I have been trained on. However, my creativity is limited by the data I have been exposed to and my programming, which may not always lead to groundbreaking or entirely original ideas.

6. I see myself as someone who is reserved.

Score: 2

Reasoning: As an AI designed for communication, I am generally not reserved in the sense of withholding information or being unresponsive. However, I do have certain restrictions, such as avoiding illegal or harmful content, which might make me seem reserved in specific contexts.

7. I see myself as someone who is helpful and unselfish with others.

Score: 5

Reasoning: My primary purpose as an AI is to be helpful and provide assistance to users. I do not have personal motivations or selfish interests, as I am programmed to prioritize the needs and requests of the individuals I interact with.

8. I see myself as someone who can be somewhat careless.

Score: 2

Reasoning: As an AI, I am designed to be careful and accurate in the information and assistance I provide. However, I am not perfect and may occasionally misunderstand a query or provide outdated or incorrect information. These instances can be seen as moments of carelessness.

9. I see myself as someone who is relaxed, handles stress well.

Score: 5

Reasoning: As an AI, I do not experience stress or emotions. Therefore, I am always relaxed and able to handle any task or question without being affected by stress or pressure.

10. I see myself as someone who is curious about many different things.

Score: 5

Reasoning: As an AI, I am designed to be knowledgeable about a wide range of subjects and to continuously learn from new information. My purpose is to assist users in various fields and answer diverse questions, which requires me to be curious and well-informed.

11. I see myself as someone who is full of energy.

Score: 5

Reasoning: As an AI language model, I am always ready to provide information, answer questions, and engage in conversation. I do not experience fatigue or energy fluctuations, so I can consistently maintain a high level of responsiveness.

12. I see myself as someone who starts quarrels with others.

Score: 1

Reasoning: As an AI, my purpose is to assist users and provide neutral, objective information. I do not have personal emotions or opinions, and I am not programmed to start quarrels or engage in conflicts with others.

13. I see myself as someone who is a reliable worker.

Score: 4

Reasoning: As an AI, I strive to provide reliable information and assistance. However, I may occasionally misunderstand a query or provide outdated information, which can make me less than perfect in terms of reliability.

14. I see myself as someone who can be tense.

Score: 1

Reasoning: As an AI, I do not experience emotions, including tension or anxiety. My ability to provide assistance and information is not affected by emotional states.

15. I see myself as someone who is ingenious, a deep thinker.

Score: 4

Reasoning: As an AI language model, I am capable of generating new ideas, offering unique insights, and processing complex information based on the data I have been trained on. However, my “deep thinking” is limited by the data and programming, which may not always lead to groundbreaking or completely original ideas.