How far can bias go? -- Tracing bias from pretraining data to alignment

• URL: http://arxiv.org/abs/2411.19240v1
• Date: Thu, 28 Nov 2024 16:20:25 GMT
• Title: How far can bias go? -- Tracing bias from pretraining data to alignment
• Authors: Marion Thaler, Abdullatif Köksal, Alina Leidinger, Anna Korhonen, Hinrich Schütze,
• Abstract summary: This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs. Our findings reveal that biases present in pre-training data are amplified in model outputs.
• Score: 54.51310112013655
• License:
• Abstract: As LLMs are increasingly integrated into user-facing applications, addressing biases that perpetuate societal inequalities is crucial. While much work has gone into measuring or mitigating biases in these models, fewer studies have investigated their origins. Therefore, this study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs, focusing on the Dolma dataset and the OLMo model. Using zero-shot prompting and token co-occurrence analyses, we explore how biases in training data influence model outputs. Our findings reveal that biases present in pre-training data are amplified in model outputs. The study also examines the effects of prompt types, hyperparameters, and instruction-tuning on bias expression, finding instruction-tuning partially alleviating representational bias while still maintaining overall stereotypical gender associations, whereas hyperparameters and prompting variation have a lesser effect on bias expression. Our research traces bias throughout the LLM development pipeline and underscores the importance of mitigating bias at the pretraining stage.

Related papers

• Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection [5.800102484016876]
  Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content. This paper presents a systematic framework grounded in social psychology theories to investigate explicit and implicit biases in LLMs.
  arXiv  Detail & Related papers  (2025-01-04T14:08:52Z)
• Model Debiasing by Learnable Data Augmentation [19.625915578646758]
  This paper proposes a novel 2-stage learning pipeline featuring a data augmentation strategy able to regularize the training. Experiments on synthetic and realistic biased datasets show state-of-the-art classification accuracy, outperforming competing methods.
  arXiv  Detail & Related papers  (2024-08-09T09:19:59Z)
• Less can be more: representational vs. stereotypical gender bias in facial expression recognition [3.9698529891342207]
  Machine learning models can inherit biases from their training data, leading to discriminatory or inaccurate predictions. This paper investigates the propagation of demographic biases from datasets into machine learning models. We focus on the gender demographic component, analyzing two types of bias: representational and stereotypical.
  arXiv  Detail & Related papers  (2024-06-25T09:26:49Z)
• Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models [23.65626682262062]
  We quantify bias amplification in pretraining and after fine-tuning on three families of vision-and-language models. Overall, we find that bias amplification in pretraining and after fine-tuning are independent.
  arXiv  Detail & Related papers  (2023-10-26T16:19:19Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• Targeted Data Augmentation for bias mitigation [0.0]
  We introduce a novel and efficient approach for addressing biases called Targeted Data Augmentation (TDA) Unlike the laborious task of removing biases, our method proposes to insert biases instead, resulting in improved performance. To identify biases, we annotated two diverse datasets: a dataset of clinical skin lesions and a dataset of male and female faces.
  arXiv  Detail & Related papers  (2023-08-22T12:25:49Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• Feature-Level Debiased Natural Language Understanding [86.8751772146264]
  Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets. We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias. DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
  arXiv  Detail & Related papers  (2022-12-11T06:16:14Z)
• General Greedy De-bias Learning [163.65789778416172]
  We propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and the base model like gradient descent in functional space. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge.
  arXiv  Detail & Related papers  (2021-12-20T14:47:32Z)
• Balancing out Bias: Achieving Fairness Through Training Reweighting [58.201275105195485]
  Bias in natural language processing arises from models learning characteristics of the author such as gender and race. Existing methods for mitigating and measuring bias do not directly account for correlations between author demographics and linguistic variables. This paper introduces a very simple but highly effective method for countering bias using instance reweighting.
  arXiv  Detail & Related papers  (2021-09-16T23:40:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.