MoVa: Towards Generalizable Classification of Human Morals and Values
Identifying human morals and values embedded in language is essential to empirical studies of communication. However, researchers often face substantial difficulty navigating the diversity of theoretical frameworks and data available for their analysis. Here, we contribute MoVa, a well-documented suite of resources for generalizable classification of human morals and values, consisting of (1) 16 labeled datasets and benchmarking results from four theoretically-grounded frameworks; (2) a lightweight LLM prompting strategy that outperforms fine-tuned models across multiple domains and frameworks; and (3) a new application that helps evaluate psychological surveys. In practice, we specifically recommend a classification strategy, all@once, that scores all related concepts simultaneously, resembling the well-known multi-label classifier chain. The data and methods in MoVa can facilitate many fine-grained interpretations of human and machine communication, with potential implications for the alignment of machine behavior.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Lessons Without Borders? Evaluating Cultural Alignment of LLMs Using Multilingual Story Moral Generation
Stories are key to transmitting values across cultures, but their interpretation varies across linguistic and cultural contexts. Thus, we introduce multilingual story moral generation as a novel culturally grounded evalu…
Semantic SimilarityA Corpus for Understanding and Generating Moral Stories
Teaching morals is one of the most important purposes of storytelling. An essential ability for understanding and writing moral stories is bridging story plots and implied morals. Its challenges mainly lie in: (1) graspi…
RetrievalV-MORALS: Visual Morse Graph-Aided Estimation of Regions of Attraction in a Learned Latent Space
Reachability analysis has become increasingly important in robotics to distinguish safe from unsafe states. Unfortunately, existing reachability and safety analysis methods often fall short, as they typically require kno…
CounterMoral: Editing Morals in Language Models
Recent advancements in language model technology have significantly enhanced the ability to edit factual information. Yet, the modification of moral judgments, a crucial aspect of aligning models with human values, has g…
The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments
An audience's prior beliefs and morals are strong indicators of how likely they will be affected by a given argument. Utilizing such knowledge can help focus on shared values to bring disagreeing parties towards agreemen…