Related papers: Contextualized moral inference
Text data are being used as a lens through which human cognition can be studied at a large scale. Methods like emotion analysis are now in the standard toolkit of computational social scientists but typically rely on third-person annotation…
Modern AI and robotic systems are characterized by a high and ever-increasing level of autonomy. At the same time, their applications in fields such as autonomous driving, service robotics and digital personal assistants move closer to…
As AI systems become pervasive, grounding their behavior in human values is critical. Prior work suggests that language models (LMs) exhibit limited inherent moral reasoning, leading to calls for explicit moral teaching. However,…
In this paper, we aim to extract commonsense knowledge to improve machine reading comprehension. We propose to represent relations implicitly by situating structured knowledge in a context instead of relying on a pre-defined set of…
In natural language the intended meaning of a word or phrase is often implicit and depends on the context. In this work, we propose a simple yet effective method for sentiment analysis using contextual embeddings and a self-attention…
Gender bias is highly impacting natural language processing applications. Word embeddings have clearly been proven both to keep and amplify gender biases that are present in current data sources. Recently, contextualized word embeddings…
Understanding human actions is a key problem in computer vision. However, recognizing actions is only the first step of understanding what a person is doing. In this paper, we introduce the problem of predicting why a person has performed…
One of today's most significant societal challenges is building AI systems whose behaviour, or the behaviour it enables within communities of interacting agents (human and artificial), aligns with human values. To address this challenge, we…
Automated prediction of valence, one key feature of a person's emotional state, from individuals' personal narratives may provide crucial information for mental healthcare (e.g. early diagnosis of mental diseases, supervision of disease…
We present a general approach to automating ethical decisions, drawing on machine learning and computational social choice. In a nutshell, we propose to learn a model of societal preferences, and, when faced with a specific ethical dilemma…
Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual…
While previous sentiment analysis research has concentrated on the interpretation of explicitly stated opinions and attitudes, this work initiates the computational study of a type of opinion implicature (i.e., opinion-oriented inference)…
Advances in artificial intelligence (AI) raise important questions about whether people view moral evaluations by AI systems similarly to human-generated moral evaluations. We conducted a modified Moral Turing Test (m-MTT), inspired by…
Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques…
Automated sentiment analysis and opinion mining is a complex process concerning the extraction of useful subjective information from text. The explosion of user generated content on the Web, especially the fact that millions of users, on a…
Recent adoption of conversational information systems has expanded the scope of user queries to include complex tasks such as personal advice-seeking. However, we identify a specific type of sought advice-a request for a moral judgment…
We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g.,…
As artificial intelligence rapidly transforms society, developers and policymakers struggle to anticipate which applications will face public moral resistance. We propose that these judgments are not idiosyncratic but systematic and…
In high-stakes AI-supported decisions, considerations are not purely technical but involve moral judgments about fairness, responsibility, and harm. While prior research has focused mainly on functional or behavioral alignment, this paper…
Human behaviors are often guided or constrained by social norms, which are defined as shared, commonsense rules. For example, underlying an action ``\textit{report a witnessed crime}" are social norms that inform our conduct, such as…