Developing moral awareness in intelligent systems has shifted from a topic of philosophical inquiry to a critical and practical issue in artificial intelligence over the past decades. However, automated inference of everyday moral situations remains an under-explored problem. We present a text-based approach that predicts people's intuitive judgment of moral vignettes. Our methodology builds on recent work in contextualized language models and textual inference of moral sentiment. We show that a contextualized representation offers a substantial advantage over alternative representations based on word embeddings and emotion sentiment in inferring human moral judgment, evaluated and reflected in three independent datasets from moral psychology. We discuss the promise and limitations of our approach toward automated textual moral reasoning.
Pragmatic Inference for Improving Social Reasoning Generalization in Large Language Models
Indiana University Indianapolis(印第安纳大学印第安纳波利斯分校);Nanyang Technological University(南洋理工大学);University of Mississippi(密苏里大学);Northeastern University(东北大学);Qualcomm(高通公司);Michigan State University(密歇根州立大学)
ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation
School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算与信息系统学院);Institute of Advanced Intelligence and Computing, A*STAR(新加坡科研局先进智能与计算研究所)
Learning to Diagnose and Correct Moral Errors in Large Language Models
University of Mississippi(密西根州立大学);Nanyang Technological University(南洋理工大学);Northeastern University(东北大学);AWS AI Labs(AWS AI实验室);Johns Hopkins University(约翰霍普金斯大学);Qualcomm(高通);Michigan State University(密西根州立大学);Indiana University Indianapolis(印第安纳大学印第安纳波利斯分校)
Dr.Quad at MEDIQA 2019: Towards Textual Inference and Question Entailment using contextualized representations
Carnegie Mellon University(卡内基梅隆大学)
本文介绍了Quad博士团队提交的ACL-BioNLP 2019共享任务,即医学领域的文本推理和问题蕴涵。我们的系统基于Liu et al.(2019)的先前工作,该工作使用多任务目标函数进行文本蕴涵。在这项工作中,我们探讨了不同的战略,推广国家的最先进的语言理解模型的专业医疗领域。我们在共享任务上的结果表明,通过数据增强整合领域知识是应对医学等专业领域所带来挑战的有力策略。
LML: A Novel Lexicon for the Moral Foundation of Liberty
Universidad Polit\'ecnica de Madrid, Spain University of Twente, Enschede, The Netherlands European Commission, Joint Research Centre (DG JRC), Ispra, Italy ISI Foundation, Turin, Italy