认识自己,提高自己:个性化的LLM为自我认识和道德提升
Alberto Giubilini1, Sebastian Porsdam Mann2,3, Cristina Voinea4
1Uehiro Oxford Institute and Wellcome Centre for Ethics and Humanities, University of Oxford, Oxford, UK. alberto.giubilini@uehiro.ox.ac.uk.
Science and engineering ethics
|November 21, 2024
概括
个性化大型语言模型 (LLM) 可以充当人工道德顾问 (AMA),使用个人数据来指导不断发展的个人价值观和自我创造. 这种方法提高了自我认识,并解决了当前AMA系统的局限性.
科学领域:
- 人工智能的人工智能
- 伦理学 伦理学 伦理学
- 人与计算机的交互
背景情况:
- 当前的人工道德顾问 (AMA) 建议往往依赖于静态的,预先确定的价值观,或要求用户进行广泛的内观自我认识.
- 个人道德是动态的,可以随着时间的推移而变化,这对现有的AMA框架构成了挑战.
研究的目的:
- 提出个性化大型语言模型 (LLM),以个人数据进行训练,作为人工道德咨询的新方法.
- 探索基于LLM的AMA如何解释个人道德的动态性质,促进自我认识和自我创造.
主要方法:
- 基于LLM的概念建议,基于用户特定数据 (写作,交互) 训练的AMA.
- 利用过去和现在的用户数据来推断和阐明不断变化的价值观和偏好.
- 利用人工智能来反思个人身份,期望的未来自我和可行的目标.
主要成果:
- 基于LLM的AMA可以通过反映用户的动态价值来提供个性化的道德指导.
- 这些系统可以增强用户的自我认识,并协助自我创造和个人发展的过程.
- 提出的方法解决了基于固定值或要求内观能力的AMAs的局限性.
结论:
- 个性化的LLM为开发适应个人的道德进化的人工道德顾问提供了一个有希望的途径.
- 需要进一步的技术开发来确定这些基于LLM的AMA的可行性.
- 这种方法比静态或依赖内观测的AMA系统具有显著的进步.
相关概念视频
Self-Schemas
31.0K
In general, a schema is a mental construct consisting of a cluster or collection of related concepts (Bartlett, 1932). There are many different types of schemata, and they all have one thing in common: schemata are a method of organizing information that allows the brain to work more efficiently. When a schema is activated, the brain makes immediate assumptions about the person or object being observed.
31.0K
The Sense of Self: Reflected Self-Appraisal and Social Comparison
49.7K
According to Charles Cooley, we base our image on what we think other people see (Cooley 1902). We imagine how we must appear to others, then react to this speculation. We don certain clothes, prepare our hair in a particular manner, wear makeup, use cologne, and the like—all with the notion that our presentation of ourselves is going to affect how others perceive us. We expect a certain reaction, and, if lucky, we get the one we desire and feel good about it. But more than that, Cooley...
49.7K
Self-Evaluation: Self-Enhancement and Self-Verification
5.2K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
5.2K
Metacognition
138
Metacognition is a conscious process where individuals are aware of their cognitive and executive processes, such as planning before solving a problem or self-monitoring during reading. For instance, a writer may need help with composing a piece. The situation involves a writer who is working on a piece of writing, but while doing so, they realize that something is missing. They notice that their characters lack depth or details. This realization occurs because the writer is reflecting on their...
138
Language and Cognition
325
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
325
Self-Presentation: Self-Monitoring and Self-Handicapping
38.8K
People can go to great lengths to protect their self-image and present themselves in ways that they want others to see them. Sociologist Erving Goffman presented the idea that a person is like an actor on a stage. Calling his theory dramaturgy, Goffman believed that we use “impression management” to present ourselves to others as we hope to be perceived. Each situation is a new scene, and individuals perform different roles depending on who is present (Goffman, 1959). Think about...
38.8K


