相关论文: CounterMoral: Editing Morals in Language Models

Counterfactual reasoning is widely recognized as one of the most challenging and intricate aspects of causality in artificial intelligence. In this paper, we evaluate the performance of large language models (LLMs) in counterfactual…

This paper discusses and contains offensive content. Language models (LMs) are used in decision-making systems and as interactive assistants. However, how well do these models making judgements align with the diversity of human values,…

We test the hypothesis that language models trained with reinforcement learning from human feedback (RLHF) have the capability to "morally self-correct" -- to avoid producing harmful outputs -- if instructed to do so. We find strong…

Conceptual analysis -- proposing definitions and refining them through counterexamples -- is central to philosophical methodology. We study whether language models can perform this task through iterated analysis and repair chains: one model…

As humans, we consistently interact with our peers and receive feedback in the form of natural language. This language feedback allows us to maintain appropriate behavior, and rectify potential errors. The question arises naturally: can we…

Large language models are increasingly influencing human moral decisions, yet current approaches focus primarily on evaluating rather than actively steering their moral decisions. We formulate this as an out-of-distribution moral alignment…

This study explores computational approaches for measuring moral foundations (MFs) in non-English corpora. Since most resources are developed primarily for English, cross-linguistic applications of moral foundation theory remain limited.…

Large Language Models (LLMs) have made significant strides in the field of artificial intelligence, showcasing their ability to interact with humans and influence human cognition through information dissemination. However, recent studies…

As robots become increasingly integrated into daily life, understanding responses to robot mistreatment carries important ethical and design implications. This mixed-methods study (N = 201) examined how anthropomorphic levels and moral…

This work contributes to the field of Machine Ethics (ME) benchmarking, which develops tests to assess whether intelligent systems accurately represent human values and act accordingly. We identify three major issues with current ME…

In recent years machine translation has become very successful for high-resource language pairs. This has also sparked new interest in research on the automatic translation of low-resource languages, including Indigenous languages. However,…

We evaluate the moral alignment of LLMs with human preferences in multilingual trolley problems. Building on the Moral Machine experiment, which captures over 40 million human judgments across 200+ countries, we develop a cross-lingual…

Large language models (LLMs) make it easy to rewrite a text in any style -- e.g. to make it more polite, persuasive, or more positive -- but evaluation thereof is not straightforward. A challenge lies in measuring content preservation: that…

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

Machine learning (ML) enabled classification models are becoming increasingly popular for tackling the sheer volume and speed of online misinformation and other content that could be identified as harmful. In building these models, data…

Large Language Models (LLMs) have demonstrated impressive capabilities in generating fluent text, as well as tendencies to reproduce undesirable social biases. This study investigates whether LLMs reproduce the moral biases associated with…

Anthropomorphic language describing artificial intelligence (AI) is widespread in media, policy, and everyday discourse; so too are discussions of AI bad behavior, from hallucinations to inappropriate comments. How does humanizing language…

Counterspeech has emerged as a popular and effective strategy for combating online hate speech, sparking growing research interest in automating its generation using language models. However, the field still lacks standardised evaluation…

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update…

Large language models (LLMs) inevitably encode outdated or incorrect knowledge. Updating, deleting, and forgetting such knowledge is important for alignment, safety, and other issues. To address this issue, model editing has emerged as a…