# The Golden Rule as a Heuristic to Measure the Fairness of Texts Using Machine Learning

arXiv: https://arxiv.org/abs/2111.00107 · HTML: https://mlsanity.com/paper/2111.00107/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 58 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Universal Sentence Encoder](https://mlsanity.com/paper/1803.11175/) (2018)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [The Geometry of Culture: Analyzing Meaning through Word Embeddings](https://mlsanity.com/paper/1803.09288/) (2018)
- [word2vec Parameter Learning Explained](https://mlsanity.com/paper/1411.2738/) (2014)

## Built on by (most cited first, 2 of 2)

- [(Machine) Learning to Be Like Thee? For Algorithm Education, Not Training](https://mlsanity.com/paper/2305.12157/) (2023)
- [Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries](https://mlsanity.com/paper/2603.04413/) (2026)

## Abstract (arXiv)

In this paper we present a natural language programming framework to consider how the fairness of acts can be measured. For the purposes of the paper, a fair act is defined as one that one would be accepting of if it were done to oneself. The approach is based on an implementation of the golden rule (GR) in the digital domain. Despite the GRs prevalence as an axiom throughout history, no transfer of this moral philosophy into computational systems exists. In this paper we consider how to algorithmically operationalise this rule so that it may be used to measure sentences such as: the boy harmed the girl, and categorise them as fair or unfair. A review and reply to criticisms of the GR is made. A suggestion of how the technology may be implemented to avoid unfair biases in word embeddings is made - given that individuals would typically not wish to be on the receiving end of an unfair act, such as racism, irrespective of whether the corpus being used deems such discrimination as praiseworthy.