# Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias

arXiv: https://arxiv.org/abs/2204.10365 · HTML: https://mlsanity.com/paper/2204.10365/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 84 of its 133 references that are in the map.
- First posted on arXiv 21 Apr 2022.

## Builds on (most cited first, 30 of 84)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Pre-trained Models for Natural Language Processing: A Survey](https://mlsanity.com/paper/2003.08271/) (2020)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [FastText.zip: Compressing text classification models](https://mlsanity.com/paper/1612.03651/) (2016)
- [One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling](https://mlsanity.com/paper/1312.3005/) (2013)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)

## Built on by (most cited first, 8 of 8)

- [Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models](https://mlsanity.com/paper/2206.08325/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [Math anxiety and associative knowledge structure are entwined in psychology students but not in Large Language Models like GPT-3.5 and GPT-4o](https://mlsanity.com/paper/2511.01558/) (2025)
- [Cognitive network science reveals bias in GPT-3, ChatGPT, and GPT-4 mirroring math anxiety in high-school students](https://mlsanity.com/paper/2305.18320/) (2023)
- [PhDGPT: Introducing a psychometric and linguistic dataset about how large language models perceive graduate students and professors in psychology](https://mlsanity.com/paper/2411.10473/) (2024)
- [REDAffectiveLM: Leveraging Affect Enriched Embedding and Transformer-based Neural Language Model for Readers' Emotion Detection](https://mlsanity.com/paper/2301.08995/) (2023)
- [Blacks is to Anger as Whites is to Joy? Understanding Latent Affective Bias in Large Pre-trained Neural Language Models](https://mlsanity.com/paper/2301.09003/) (2023)
- [Towards Exploring Fairness in Visual Transformer based Natural and GAN Image Detection Systems](https://mlsanity.com/paper/2310.12076/) (2023)

## Abstract (arXiv)

The remarkable progress in Natural Language Processing (NLP) brought about by deep learning, particularly with the recent advent of large pre-trained neural language models, is brought into scrutiny as several studies began to discuss and report potential biases in NLP applications. Bias in NLP is found to originate from latent historical biases encoded by humans into textual data which gets perpetuated or even amplified by NLP algorithm. We present a survey to comprehend bias in large pre-trained language models, analyze the stages at which they occur in these models, and various ways in which these biases could be quantified and mitigated. Considering wide applicability of textual affective computing based downstream tasks in real-world systems such as business, healthcare, education, etc., we give a special emphasis on investigating bias in the context of affect (emotion) i.e., Affective Bias, in large pre-trained language models. We present a summary of various bias evaluation corpora that help to aid future research and discuss challenges in the research on bias in pre-trained language models. We believe that our attempt to draw a comprehensive view of bias in pre-trained language models, and especially the exploration of affective bias will be highly beneficial to researchers interested in this evolving field.