Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models

• URL: http://arxiv.org/abs/2407.19345v3
• Date: Mon, 10 Feb 2025 13:18:25 GMT
• Title: Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models
• Authors: Gleb Kuzmin, Neemesh Yadav, Ivan Smirnov, Timothy Baldwin, Artem Shelmanov,
• Abstract summary: We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality. We identify the potentially biased model predictions and, instead of discarding them, we remove bias from these predictions using LEACE -- a post-processing debiasing method. Experiments on text classification datasets with encoder-based classification models demonstrate that selective debiasing helps to reduce the performance gap between post-processing methods and debiasing techniques.
• Score: 27.578390085427156
• License:
• Abstract: We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The method draws inspiration from selective classification, where at inference time, predictions with low quality, as indicated by their uncertainty scores, are discarded. In our approach, we identify the potentially biased model predictions and, instead of discarding them, we remove bias from these predictions using LEACE -- a post-processing debiasing method. To select problematic predictions, we propose a bias quantification approach based on KL divergence, which achieves better results than standard uncertainty quantification methods. Experiments on text classification datasets with encoder-based classification models demonstrate that selective debiasing helps to reduce the performance gap between post-processing methods and debiasing techniques from the at-training and pre-processing categories.

Related papers

• CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges [21.580762639442913]
  We introduce CalibraEval, a novel label-free method for mitigating selection bias during inference. CalibraEval reformulates debiasing as an optimization task aimed at adjusting observed prediction distributions to align with unbiased prediction distributions. We show that CalibraEval effectively mitigates selection bias and improves performance compared to existing debiasing methods.
  arXiv  Detail & Related papers  (2024-10-20T13:47:39Z)
• Editable Fairness: Fine-Grained Bias Mitigation in Language Models [52.66450426729818]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases. FAST surpasses state-of-the-art baselines with superior debiasing performance. This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Trustworthy Classification through Rank-Based Conformal Prediction Sets [9.559062601251464]
  We propose a novel conformal prediction method that employs a rank-based score function suitable for classification models. Our approach constructs prediction sets that achieve the desired coverage rate while managing their size. Our contributions include a novel conformal prediction method, theoretical analysis, and empirical evaluation.
  arXiv  Detail & Related papers  (2024-07-05T10:43:41Z)
• Towards Better Certified Segmentation via Diffusion Models [62.21617614504225]
  segmentation models can be vulnerable to adversarial perturbations, which hinders their use in critical-decision systems like healthcare or autonomous driving. Recently, randomized smoothing has been proposed to certify segmentation predictions by adding Gaussian noise to the input to obtain theoretical guarantees. In this paper, we address the problem of certifying segmentation prediction using a combination of randomized smoothing and diffusion models.
  arXiv  Detail & Related papers  (2023-06-16T16:30:39Z)
• Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations [4.960902915238239]
  We propose a theoretically guaranteed model-agnostic balancing approach that can be applied to any existing debiasing method. The proposed approach makes full use of unbiased data by alternatively correcting model parameters learned with biased data, and adaptively learning balance coefficients of biased samples for further debiasing.
  arXiv  Detail & Related papers  (2023-04-17T08:56:55Z)
• Calibrated Selective Classification [34.08454890436067]
  We develop a new approach to selective classification in which we propose a method for rejecting examples with "uncertain" uncertainties. We present a framework for learning selectively calibrated models, where a separate selector network is trained to improve the selective calibration error of a given base model. We demonstrate the empirical effectiveness of our approach on multiple image classification and lung cancer risk assessment tasks.
  arXiv  Detail & Related papers  (2022-08-25T13:31:09Z)
• Model-agnostic bias mitigation methods with regressor distribution control for Wasserstein-based fairness metrics [0.6509758931804478]
  We propose a bias mitigation methodology based upon the construction of post-processed models with fairer regressor distributions. Our novel methodology performs optimization in low-dimensional spaces and avoids expensive model retraining.
  arXiv  Detail & Related papers  (2021-11-19T17:31:22Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)
• Selective Classification via One-Sided Prediction [54.05407231648068]
  One-sided prediction (OSP) based relaxation yields an SC scheme that attains near-optimal coverage in the practically relevant high target accuracy regime. We theoretically derive bounds generalization for SC and OSP, and empirically we show that our scheme strongly outperforms state of the art methods in coverage at small error levels.
  arXiv  Detail & Related papers  (2020-10-15T16:14:27Z)
• Towards Debiasing NLU Models from Unknown Biases [70.31427277842239]
  NLU models often exploit biases to achieve high dataset-specific performance without properly learning the intended task. We present a self-debiasing framework that prevents models from mainly utilizing biases without knowing them in advance.
  arXiv  Detail & Related papers  (2020-09-25T15:49:39Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)

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.