# Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor

arXiv: https://arxiv.org/abs/1905.09866 · HTML: https://mlsanity.com/paper/1905.09866/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 May 2019.

## Built on by (most cited first, 27 of 27)

- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- [BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?](https://mlsanity.com/paper/2105.04949/) (2021)
- [BERTIN: Efficient Pre-Training of a Spanish Language Model using Perplexity Sampling](https://mlsanity.com/paper/2207.06814/) (2022)
- [How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing](https://mlsanity.com/paper/2205.10095/) (2022)
- [How sensitive are translation systems to extra contexts? Mitigating gender bias in Neural Machine Translation models through relevant contexts](https://mlsanity.com/paper/2205.10762/) (2022)
- [Trustworthy Social Bias Measurement](https://mlsanity.com/paper/2212.11672/) (2022)
- [Biased AI can Influence Political Decision-Making](https://mlsanity.com/paper/2410.06415/) (2024)
- [Construction Artifacts in Metaphor Identification Datasets](https://mlsanity.com/paper/2311.00790/) (2023)
- [Hire Me or Not? Examining Language Model's Behavior with Occupation Attributes](https://mlsanity.com/paper/2405.06687/) (2024)
- [Fine-Tuned LLMs are "Time Capsules" for Tracking Societal Bias Through Books](https://mlsanity.com/paper/2502.05331/) (2025)
- [Undesirable Biases in NLP: Addressing Challenges of Measurement](https://mlsanity.com/paper/2211.13709/) (2022)
- [A methodology to characterize bias and harmful stereotypes in natural language processing in Latin America](https://mlsanity.com/paper/2207.06591/) (2022)
- [STOP! Benchmarking Large Language Models with Sensitivity Testing on Offensive Progressions](https://mlsanity.com/paper/2409.13843/) (2024)
- [Think Again! The Effect of Test-Time Compute on Preferences, Opinions, and Beliefs of Large Language Models](https://mlsanity.com/paper/2505.19621/) (2025)
- [Counteracts: Testing Stereotypical Representation in Pre-trained Language Models](https://mlsanity.com/paper/2301.04347/) (2023)
- [Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models](https://mlsanity.com/paper/2306.09752/) (2023)
- [Explaining Relation Classification Models with Semantic Extents](https://mlsanity.com/paper/2308.02193/) (2023)
- [LLM-Assisted Content Conditional Debiasing for Fair Text Embedding](https://mlsanity.com/paper/2402.14208/) (2024)
- [Text analysis and deep learning: A network approach](https://mlsanity.com/paper/2110.04151/) (2021)
- [A Bayesian approach to uncertainty in word embedding bias estimation](https://mlsanity.com/paper/2306.09066/) (2023)
- [She had Cobalt Blue Eyes: Prompt Testing to Create Aligned and Sustainable Language Models](https://mlsanity.com/paper/2310.18333/) (2023)
- [FairBelief -- Assessing Harmful Beliefs in Language Models](https://mlsanity.com/paper/2402.17389/) (2024)
- [An Effective, Robust and Fairness-aware Hate Speech Detection Framework](https://mlsanity.com/paper/2409.17191/) (2024)
- [MUTEX: Leveraging Multilingual Transformers and Conditional Random Fields for Enhanced Urdu Toxic Span Detection](https://mlsanity.com/paper/2603.05057/) (2026)
- [Language, Language Models, and What We're Talking About](https://mlsanity.com/paper/2609.03577/) (2026)

## Abstract (arXiv)

Analogies such as "man is to king as woman is to X" are often used to illustrate the amazing power of word embeddings. Concurrently, they have also been used to expose how strongly human biases are encoded in vector spaces built on natural language, like "man is to computer programmer as woman is to homemaker". Recent work has shown that analogies are in fact not such a diagnostic for bias, and other methods have been proven to be more apt to the task. However, beside the intrinsic problems with the analogy task as a bias detection tool, in this paper we show that a series of issues related to how analogies have been implemented and used might have yielded a distorted picture of bias in word embeddings. Human biases are present in word embeddings and need to be addressed. Analogies, though, are probably not the right tool to do so. Also, the way they have been most often used has exacerbated some possibly non-existing biases and perhaps hid others. Because they are still widely popular, and some of them have become classics within and outside the NLP community, we deem it important to provide a series of clarifications that should put well-known, and potentially new cases into the right perspective.