Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting

2021/10/11 by Zahra Fatemi, Xing Chen, Fatemi, Zahra +5 · 3 citations
Computer Science · #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2110.05367

openalex publication_date 2021/10/11 · openalex created_date 2021/10/25 · openalex updated_date 2026/07/28

Abstract

Existing studies addressing gender bias of pre-trained language models, usually build a small gender-neutral data set and conduct a second phase pre-training on the model with such data. However, given the limited size and concentrated focus of the gender-neutral data, catastrophic forgetting would occur during second-phase pre-training. Forgetting information in the original training data may damage the model's downstream performance by a large margin. In this work, we empirically show that catastrophic forgetting occurs in such methods by evaluating them with general NLP tasks in GLUE. Then, we propose a new method, GEnder Equality Prompt (GEEP), to improve gender fairness of pre-trained models with less forgetting. GEEP freezes the pre-trained model and learns gender-related prompts with gender-neutral data. Empirical results show that GEEP not only achieves SOTA performances on gender fairness tasks, but also forgets less and performs better on GLUE by a large margin.

Cited by

• Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
• Textual Data Bias Detection and Mitigation -- An Extensible Pipeline with Experimental Evaluation
• Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing

Related

• Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions
• LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models
• Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models
• Gender Bias in Neural Natural Language Processing
• GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations