# On Debiasing Text Embeddings Through Context Injection

arXiv: https://arxiv.org/abs/2410.12874 · HTML: https://mlsanity.com/paper/2410.12874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 31 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 27 of 27)

- [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)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models](https://mlsanity.com/paper/2104.08663/) (2021)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders](https://mlsanity.com/paper/2404.05961/) (2024)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [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)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings](https://mlsanity.com/paper/1904.04047/) (2019)
- [Debiasing Pre-trained Contextualised Embeddings](https://mlsanity.com/paper/2101.09523/) (2021)
- [AnglE-optimized Text Embeddings](https://mlsanity.com/paper/2309.12871/) (2023)
- [SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations](https://mlsanity.com/paper/2406.11171/) (2024)
- [What are the biases in my word embedding?](https://mlsanity.com/paper/1812.08769/) (2018)
- [Debiasing Embeddings for Reduced Gender Bias in Text Classification](https://mlsanity.com/paper/1908.02810/) (2019)
- [LangProp: A code optimization framework using Large Language Models applied to driving](https://mlsanity.com/paper/2401.10314/) (2024)
- [An Analysis of Hierarchical Text Classification Using Word Embeddings](https://mlsanity.com/paper/1809.01771/) (2018)

## Abstract (arXiv)

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into vectors, via embedding models. However, it has been shown that these embeddings capture and perpetuate biases already present in text. While a few techniques have been proposed to debias embeddings, they do not take advantage of the recent advances in context understanding of modern embedding models. In this paper, we fill this gap by conducting a review of 19 embedding models by quantifying their biases and how well they respond to context injection as a mean of debiasing. We show that higher performing models are more prone to capturing biases, but are also better at incorporating context. Surprisingly, we find that while models can easily embed affirmative semantics, they fail at embedding neutral semantics. Finally, in a retrieval task, we show that biases in embeddings can lead to non-desirable outcomes. We use our new-found insights to design a simple algorithm for top k retrieval, where k is dynamically selected. We show that our algorithm is able to retrieve all relevant gendered and neutral chunks.