大型语言模型与人类价值观的强大和弱弱对齐
Mehdi Khamassi1, Marceau Nahon2, Raja Chatila3
1Institute of Intelligent Systems and Robotics, Sorbonne University/CNRS, 75005, Paris, France. mehdi.khamassi@sorbonne-universite.fr.
Scientific reports
|August 21, 2024
概括
人工智能 (AI) 的调整需要强有力的价值调整,需要人工智能的认知能力来理解人类的价值观和防止伤害. 当前的人工智能系统在识别对人类价值观的风险方面表现出失败.
科学领域:
- 人工智能的人工智能
- 人工智能伦理学
- 认知科学 认知科学
背景情况:
- 人工智能系统需要与人类价值观保持一致,以尽量减少对社会的伤害.
- 目前的AI调整研究主要集中在技术方面,忽视了更深层次的要求.
- 强大和弱弱的人工智能价值调整之间的区别对于强大的安全至关重要.
研究的目的:
- 为了区分强大和弱弱的AI价值调整.
- 突出人工智能识别和防止价值浮动情况的认知先决条件.
- 分析人工智能模型中人类价值观的语义表示.
主要方法:
- 区分强 (认知能力) 和弱 (统计) 的价值对齐.
- 介绍大型语言模型 (LLM) 的基于提示的评估,如ChatGPT,Gemini和Copilot.
- 分析词语嵌入来比较人类和人工智能语义表示的价值观.
- 提出一个新的思维实验:"中文房带有单词过渡字典".
主要成果:
- 法律学士在识别人类价值观可能受到损害的情况时表现出失败.
- 人工智能对人类价值观的语义表示与人类表示不同,正如词嵌入分析所显示的那样.
- 目前的研究方向侧重于弱对齐,提供没有保证真实性的统计解决方案.
结论:
- 强大的AI价值调整需要认知能力来真正理解和推理人类价值观.
- 仅靠技术AI调整方法是不足以确保AI系统维护人类价值观的.
- 需要进一步的研究来开发具有强大的认知能力的AI,以实现真正的价值调整.
相关概念视频
Language and Cognition
339
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.
339
Language
206
Language is a unique communication system that uses words and systematic rules to organize and transmit information. Unlike other forms of communication, which may involve postures, movements, odors, or vocalizations, language relies on symbols and grammar. This makes human communication distinct from that of other species, who also communicate but do not use language in the same way humans do.
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
206
Language Development
329
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
329
Improving Translational Accuracy
9.5K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.5K
Professional Values
6.5K
Nurses are responsible for caring for patients during birth, death, illness, and healing. Professional values guide the decisions and actions that nurses make in their careers. If nurses know the decisions and actions to take, providing patients with exceptional care is possible.
The values that are the foundation of the nursing profession are altruism, autonomy, human dignity, and social justice.
First, altruism refers to the concern for the welfare and well-being of others without personal...
The values that are the foundation of the nursing profession are altruism, autonomy, human dignity, and social justice.
First, altruism refers to the concern for the welfare and well-being of others without personal...
6.5K
Biodiversity and Human Values
13.0K
Human civilization relies on biodiversity in many ways. Sudden changes in species biodiversity result in environmental changes that can modify weather patterns and therefore human civilizations.
13.0K


