# ADEPT: A DEbiasing PrompT Framework

arXiv: https://arxiv.org/abs/2211.05414 · HTML: https://mlsanity.com/paper/2211.05414/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 56 references that are in the map.
- First posted on arXiv 10 Nov 2022.

## Builds on (most cited first, 30 of 32)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [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)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [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)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP](https://mlsanity.com/paper/2103.00453/) (2021)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Semi-supervised Sequence Learning](https://mlsanity.com/paper/1511.01432/) (2015)
- [Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets](https://mlsanity.com/paper/2106.10328/) (2021)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://mlsanity.com/paper/2012.15859/) (2020)
- [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)
- [An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models](https://mlsanity.com/paper/2110.08527/) (2021)

## Built on by (most cited first, 21 of 21)

- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024)
- [A Survey on Fairness in Large Language Models](https://mlsanity.com/paper/2308.10149/) (2023)
- [Fairness in Large Language Models: A Taxonomic Survey](https://mlsanity.com/paper/2404.01349/) (2024)
- [From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Models](https://mlsanity.com/paper/2403.12027/) (2024)
- [Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models](https://mlsanity.com/paper/2407.08039/) (2024)
- [BendVLM: Test-Time Debiasing of Vision-Language Embeddings](https://mlsanity.com/paper/2411.04420/) (2024)
- [Large Language Model Bias Mitigation from the Perspective of Knowledge Editing](https://mlsanity.com/paper/2405.09341/) (2024)
- [No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users](https://mlsanity.com/paper/2410.07589/) (2024)
- [More of the Same: Persistent Representational Harms Under Increased Representation](https://mlsanity.com/paper/2503.00333/) (2025)
- [Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences](https://mlsanity.com/paper/2501.06795/) (2025)
- [BEADs: Bias Evaluation Across Domains](https://mlsanity.com/paper/2406.04220/) (2024)
- [The Life Cycle of Large Language Models: A Review of Biases in Education](https://mlsanity.com/paper/2407.11203/) (2024)
- [GeoBS: Information-Theoretic Quantification of Geographic Bias in AI Models](https://mlsanity.com/paper/2509.23482/) (2025)
- [Use Me Wisely: AI-Driven Assessment for LLM Prompting Skills Development](https://mlsanity.com/paper/2503.02532/) (2025)
- [When to Invoke: Refining LLM Fairness with Toxicity Assessment](https://mlsanity.com/paper/2601.09250/) (2026)
- [Collapsed Language Models Promote Fairness](https://mlsanity.com/paper/2410.04472/) (2024)
- [Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities](https://mlsanity.com/paper/2605.04127/) (2026)
- [Debias your Large Multi-Modal Model at Test-Time via Non-Contrastive Visual Attribute Steering](https://mlsanity.com/paper/2411.12590/) (2024)
- [FairNVT: Fair Classification via Noise Injection in Vision Transformers](https://mlsanity.com/paper/2604.16780/) (2026)
- [Collective Bias Mitigation via Model Routing and Collaboration](https://mlsanity.com/paper/2610.03240/) (2026)

## Abstract (arXiv)

Several works have proven that finetuning is an applicable approach for debiasing contextualized word embeddings. Similarly, discrete prompts with semantic meanings have shown to be effective in debiasing tasks. With unfixed mathematical representation at the token level, continuous prompts usually surpass discrete ones at providing a pre-trained language model (PLM) with additional task-specific information. Despite this, relatively few efforts have been made to debias PLMs by prompt tuning with continuous prompts compared to its discrete counterpart. Furthermore, for most debiasing methods that alter a PLM's original parameters, a major problem is the need to not only decrease the bias in the PLM but also to ensure that the PLM does not lose its representation ability. Finetuning methods typically have a hard time maintaining this balance, as they tend to violently remove meanings of attribute words. In this paper, we propose ADEPT, a method to debias PLMs using prompt tuning while maintaining the delicate balance between removing biases and ensuring representation ability. To achieve this, we propose a new training criterion inspired by manifold learning and equip it with an explicit debiasing term to optimize prompt tuning. In addition, we conduct several experiments with regard to the reliability, quality, and quantity of a previously proposed attribute training corpus in order to obtain a clearer prototype of a certain attribute, which indicates the attribute's position and relative distances to other words on the manifold. We evaluate ADEPT on several widely acknowledged debiasing benchmarks and downstream tasks, and find that it achieves competitive results while maintaining (and in some cases even improving) the PLM's representation ability. We further visualize words' correlation before and after debiasing a PLM, and give some possible explanations for the visible effects.