相关论文: Some Issues in Predictive Ethics Modeling: An Anno…

Language models still struggle on moral reasoning, despite their impressive performance in many other tasks. In particular, the Moral Scenarios task in MMLU (Multi-task Language Understanding) is among the worst performing tasks for many…

Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on human values; however, past work has been limited to…

Identifying the causes of a model's unfairness is an important yet relatively unexplored task. We look into this problem through the lens of training data - the major source of unfairness. We ask the following questions: How would the…

We consider a setting where agents take action by following their role models in a social network, and study strategies for a social planner to help agents by revealing whether the role models are positive or negative. Specifically, agents…

Moral cognition is a crucial yet underexplored aspect of decision-making in AI models. Regardless of the application domain, it should be a consideration that allows for ethically aligned decision-making. This paper presents a multifaceted…

In this paper we present a heuristic method to provide individual explanations for those elements in a dataset (data points) which are wrongly predicted by a given classifier. Since the general case is too difficult, in the present work we…

Artificial Intelligence (AI) systems are not intrinsically neutral and biases trickle in any type of technological tool. In particular when dealing with people, the impact of AI algorithms' technical errors originating with mislabeled data…

With the rapid development and uptake of large language models (LLMs) across high-stakes settings, it is increasingly important to ensure that LLMs behave in ways that align with human values. Existing moral benchmarks prompt LLMs with…

One open question in the study of Large Language Models (LLMs) is whether they can emulate human ethical reasoning and act as believable proxies for human judgment. To investigate this, we introduce a benchmark dataset comprising 196…

As AI systems like language models are increasingly integrated into decision-making processes affecting people's lives, it's critical to ensure that these systems have sound moral reasoning. To test whether they do, we need to develop…

Large language models (LLMs) have become increasingly pivotal in various domains due the recent advancements in their performance capabilities. However, concerns persist regarding biases in LLMs, including gender, racial, and cultural…

Large-scale pre-trained language models have demonstrated high performance on standard datasets for natural language inference (NLI) tasks. Unfortunately, these evaluations can be misleading, as although the models can perform well on…

There are several algorithms for measuring fairness of ML models. A fundamental assumption in these approaches is that the ground truth is fair or unbiased. In real-world datasets, however, the ground truth often contains data that is a…

Stance detection models may tend to rely on dataset bias in the text part as a shortcut and thus fail to sufficiently learn the interaction between the targets and texts. Recent debiasing methods usually treated features learned by small…

Artificial intelligence (AI) is advancing at a pace that raises urgent questions about how to align machine decision-making with human moral values. This working paper investigates how leading AI systems prioritize moral outcomes and what…

As LLMs excel on standard reading comprehension benchmarks, attention is shifting toward evaluating their capacity for complex abstract reasoning and inference. Literature-based benchmarks, with their rich narrative and moral depth, provide…

Moral dilemmas play an important role in theorizing both about ethical norms and moral psychology. Yet thought experiments borrowed from the philosophical literature often lack the nuances and complexity of real life. We leverage 100,000…

When large language models make ethical judgments, do their internal representations distinguish between normative frameworks, or collapse ethics into a single acceptability dimension? We probe hidden representations across five ethical…

Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decision-support systems, determining whether they encode these social nuances is critical. We…

As Machine Learning models continue to be relied upon for making automated decisions, the issue of model bias becomes more and more prevalent. In this paper, we approach training a text classifica-tion model and optimize on bias…