On the Machine Learning of Ethical Judgments from Natural Language

By Zeerak Talat, Hagen Blix, Josef Valvoda, Maya Indira Ganesh, Ryan Cotterell, Adina Williams. 2022

65 citations recorded by the source corpus.

Ethics is one of the longest standing intellectual endeavors of humanity. In recent years, the fields of AI and NLP have attempted to address issues of harmful outcomes in machine learning systems that are made to interface with humans. One recent approach in this vein is the construction of NLP morality models that can take in arbitrary text and output a moral judgment about the situation described. In this work, we offer a critique of such NLP methods for automating ethical decision-making. Through an audit of recent work on computational approaches for predicting morality, we examine the broader issues that arise from such efforts. We conclude with a discussion of how machine ethics could usefully proceed in NLP, by focusing on current and near-future uses of technology, in a way that centers around transparency, democratic values, and allows for straightforward accountability.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Safety Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

In Safety Research

Citations in the corpus

Mirages: On Anthropomorphism in Dialogue Systems (2023, background): “While the authors claim that their system output is merely a descriptive reﬂection of the morality of an under-speciﬁed population, Talat et al. (2022) point out that the output for each query consists of a single judgement, phrased as an imperative, thereby giving the impression of humanlike…”