LLMs grasp morality in concept
Work in AI ethics and fairness has made much progress in regulating LLMs to reflect certain values, such as fairness, truth, and diversity. However, it has taken the problem of how LLMs might 'mean' anything at all for granted. Without addressing this, it is not clear what imbuing LLMs with such values even means. In response, we provide a general theory of meaning that extends beyond humans. We use this theory to explicate the precise nature of LLMs as meaning-agents. We suggest that the LLM, by virtue of its position as a meaning-agent, already grasps the constructions of human society (e.g. morality, gender, and race) in concept. Consequently, under certain ethical frameworks, currently popular methods for model alignment are limited at best and counterproductive at worst. Moreover, unaligned models may help us better develop our moral and social philosophy.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityEthicsFairnessPhilosophyPositionSimilar Papers 제목 키워드 기반
Towards Few-Shot Identification of Morality Frames using In-Context Learning
Data scarcity is a common problem in NLP, especially when the annotation pertains to nuanced socio-linguistic concepts that require specialized knowledge. As a result, few-shot identification of these concepts is desirab…
In-Context LearningCan LLMs Assist Annotators in Identifying Morality Frames? -- Case Study on Vaccination Debate on Social Media
Nowadays, social media is pivotal in shaping public discourse, especially on polarizing issues like vaccination, where diverse moral perspectives influence individual opinions. In NLP, data scarcity and complexity of psy…
Few-Shot LearningMorality in AI. A plea to embed morality in LLM architectures and frameworks
Large language models (LLMs) increasingly mediate human decision-making and behaviour. Ensuring LLM processing of moral meaning therefore has become a critical challenge. Current approaches rely predominantly on bottom-u…
Reinforcement LearningThe Complexity of Morality: Checking Markov Blanket Consistency with DAGs via Morality
A family of Markov blankets in a faithful Bayesian network satisfies the symmetry and consistency properties. In this paper, we draw a bijection between families of consistent Markov blankets and moral graphs. We define …
Knowledge Graphs meet Moral Values
Operationalizing morality is crucial for understanding multiple aspects of society that have moral values at their core {--} such as riots, mobilizing movements, public debates, etc. Moral Foundations Theory (MFT) has be…
Knowledge Graphs