# Counteracts: Testing Stereotypical Representation in Pre-trained Language Models

arXiv: https://arxiv.org/abs/2301.04347 · HTML: https://mlsanity.com/paper/2301.04347/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 11 Jan 2023.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [Targeted Syntactic Evaluation of Language Models](https://mlsanity.com/paper/1808.09031/) (2018)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Assessing BERT's Syntactic Abilities](https://mlsanity.com/paper/1901.05287/) (2019)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [What do RNN Language Models Learn about Filler-Gap Dependencies?](https://mlsanity.com/paper/1809.00042/) (2018)
- [Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models](https://mlsanity.com/paper/2101.09688/) (2021)
- [Exploring BERT's Sensitivity to Lexical Cues using Tests from Semantic Priming](https://mlsanity.com/paper/2010.03010/) (2020)
- [Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items](https://mlsanity.com/paper/1808.10627/) (2018)
- [Analyzing Commonsense Emergence in Few-shot Knowledge Models](https://mlsanity.com/paper/2101.00297/) (2021)
- [Do language models learn typicality judgments from text?](https://mlsanity.com/paper/2105.02987/) (2021)
- [Relational World Knowledge Representation in Contextual Language Models: A Review](https://mlsanity.com/paper/2104.05837/) (2021)
- [Spying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words](https://mlsanity.com/paper/2005.01810/) (2020)
- [Fair is Better than Sensational:Man is to Doctor as Woman is to Doctor](https://mlsanity.com/paper/1905.09866/) (2019)

## Built on by (most cited first, 1 of 1)

- [Evaluating Large Language Models Against Human Annotators in Latent Content Analysis: Sentiment, Political Leaning, Emotional Intensity, and Sarcasm](https://mlsanity.com/paper/2501.02532/) (2025)

## Abstract (arXiv)

Recently, language models have demonstrated strong performance on various natural language understanding tasks. Language models trained on large human-generated corpus encode not only a significant amount of human knowledge, but also the human stereotype. As more and more downstream tasks have integrated language models as part of the pipeline, it is necessary to understand the internal stereotypical representation in order to design the methods for mitigating the negative effects. In this paper, we use counterexamples to examine the internal stereotypical knowledge in pre-trained language models (PLMs) that can lead to stereotypical preference. We mainly focus on gender stereotypes, but the method can be extended to other types of stereotype. We evaluate 7 PLMs on 9 types of cloze-style prompt with different information and base knowledge. The results indicate that PLMs show a certain amount of robustness against unrelated information and preference of shallow linguistic cues, such as word position and syntactic structure, but a lack of interpreting information by meaning. Such findings shed light on how to interact with PLMs in a neutral approach for both finetuning and evaluation.