# Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases

arXiv: https://arxiv.org/abs/2307.01595 · HTML: https://mlsanity.com/paper/2307.01595/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 4 Jul 2023.

## Builds on (most cited first, 30 of 33)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [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)
- [Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference](https://mlsanity.com/paper/2001.07676/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [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)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Factual Probing Is [MASK]: Learning vs. Learning to Recall](https://mlsanity.com/paper/2104.05240/) (2021)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Towards Debiasing Sentence Representations](https://mlsanity.com/paper/2007.08100/) (2020)
- [On Measuring and Mitigating Biased Inferences of Word Embeddings](https://mlsanity.com/paper/1908.09369/) (2019)
- [Linear Adversarial Concept Erasure](https://mlsanity.com/paper/2201.12091/) (2022)
- [An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models](https://mlsanity.com/paper/2110.08527/) (2021)
- [FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders](https://mlsanity.com/paper/2103.06413/) (2021)
- [CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning](https://mlsanity.com/paper/2109.07589/) (2021)
- [PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks](https://mlsanity.com/paper/2202.12499/) (2022)
- [Diverse Adversaries for Mitigating Bias in Training](https://mlsanity.com/paper/2101.10001/) (2021)
- [OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings](https://mlsanity.com/paper/2007.00049/) (2020)

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

- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [A Survey on Fairness in Large Language Models](https://mlsanity.com/paper/2308.10149/) (2023)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey](https://mlsanity.com/paper/2406.05392/) (2024)
- [Large Language Model Bias Mitigation from the Perspective of Knowledge Editing](https://mlsanity.com/paper/2405.09341/) (2024)
- [Co2PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning](https://mlsanity.com/paper/2310.12490/) (2023)
- [Identifying and Mitigating Social Bias Knowledge in Language Models](https://mlsanity.com/paper/2408.11843/) (2024)
- [Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies](https://mlsanity.com/paper/2312.01509/) (2023)
- [Potential and Challenges of Model Editing for Social Debiasing](https://mlsanity.com/paper/2402.13462/) (2024)
- [Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Management](https://mlsanity.com/paper/2502.10407/) (2025)
- [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025)
- [Paying Alignment Tax with Contrastive Learning](https://mlsanity.com/paper/2505.19327/) (2025)
- [Self-Supervised Position Debiasing for Large Language Models](https://mlsanity.com/paper/2401.01218/) (2024)
- [A Note on Bias to Complete](https://mlsanity.com/paper/2402.11710/) (2024)
- [Expert-Guided Extinction of Toxic Tokens for Debiased Generation](https://mlsanity.com/paper/2405.19299/) (2024)
- [Speciesism in Natural Language Processing Research](https://mlsanity.com/paper/2410.14194/) (2024)
- [A Heuristic Perspective on Debiasing Language Models](https://mlsanity.com/paper/2608.00622/) (2026)
- [TriCon-Fair: Triplet Contrastive Learning for Mitigating Social Bias in Pre-trained Language Models](https://mlsanity.com/paper/2511.00854/) (2025)
- [Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval](https://mlsanity.com/paper/2606.00014/) (2026)
- [The Safeguard Worked. Is the LLM System Safer?](https://mlsanity.com/paper/2609.00519/) (2026)

## Abstract (arXiv)

As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual Data Augmentation (CDA) to balance the training corpus. However, CDA slightly modifies the original corpus, limiting the representation distance between different demographic groups to a narrow range. As a result, the debiasing model easily fits the differences between counterfactual pairs, which affects its debiasing performance with limited text resources. In this paper, we propose an adversarial training-inspired two-stage debiasing model using Contrastive learning with Continuous Prompt Augmentation (named CCPA) to mitigate social biases in PLMs' encoding. In the first stage, we propose a data augmentation method based on continuous prompt tuning to push farther the representation distance between sample pairs along different demographic groups. In the second stage, we utilize contrastive learning to pull closer the representation distance between the augmented sample pairs and then fine-tune PLMs' parameters to get debiased encoding. Our approach guides the model to achieve stronger debiasing performance by adding difficulty to the training process. Extensive experiments show that CCPA outperforms baselines in terms of debiasing performance. Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs.