Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability

• URL: http://arxiv.org/abs/2412.19018v4
• Date: Tue, 11 Feb 2025 12:39:22 GMT
• Title: Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability
• Authors: Ruixi Lin, Yang You,
• Abstract summary: Large language models (LLMs) often struggle with balanced class accuracy in text classification tasks using in-context learning (ICL)<n>This paper delves deeper into the class accuracy imbalance issue, identifying that it arises because certain classes consistently receive disproportionately high ICL probabilities.<n>We introduce FuRud, a method for sample-level class probability correction.
• Score: 12.287692969438169
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) often struggle with balanced class accuracy in text classification tasks using in-context learning (ICL), hindering some practical uses due to user dissatisfaction or safety risks caused by misclassifications. Retraining LLMs to address root causes in data or model priors is neither easy nor cost-effective. This paper delves deeper into the class accuracy imbalance issue, identifying that it arises because certain classes consistently receive disproportionately high ICL probabilities, causing under-prediction and lower accuracy for others. More importantly, probability ranges affect the imbalance differently, allowing for precise, range-specific corrections. We introduce FuRud (Fuzzy Rule Optimization-based Debiasing), a method for sample-level class probability correction. FuRud tackles interpretability challenges by determining why certain classes need corrections and tailoring adjustments for each instance's class probabilities which is powered by fuzzy sets with triangular membership functions, transforming a class probability based on the range it belongs to. By solving a nonlinear integer programming problem with a labeled set of ICL class probabilities to minimize class accuracy bias (COBias) and maximize overall accuracy, each class selects an optimal correction function from 19 triangular membership functions without updating an LLM, and the selected functions correct test instances at inference. Across seven benchmark datasets, FuRud reduces COBias by over half (56%) and improves overall accuracy by 21% relatively, outperforming state-of-the-art debiasing methods.

Related papers

• Ensemble Debiasing Across Class and Sample Levels for Fairer Prompting Accuracy [17.610305828703957]
  Language models are strong few-shot learners and achieve good overall accuracy in text classification tasks. We believe that the pursuit of overall accuracy should not come from enriching the strong classes, but from raising up the weak ones. We propose a Heaviside step function based ensemble debiasing method, which enables flexible rectifications of in-context learned class probabilities.
  arXiv  Detail & Related papers  (2025-03-07T05:34:31Z)
• Risk-based Calibration for Generative Classifiers [4.792851066169872]
  We propose a learning procedure called risk-based calibration (RC) RC iteratively refines the generative classifier by adjusting its joint probability distribution according to the 0-1 loss in training samples. RC significantly outperforms closed-form learning procedures in terms of both training error and generalization error.
  arXiv  Detail & Related papers  (2024-09-05T14:06:56Z)
• Calibrated Large Language Models for Binary Question Answering [49.1574468325115]
  A well-calibrated model should produce probabilities that accurately reflect the likelihood of its predictions being correct. We propose a novel approach that utilizes the inductive Venn--Abers predictor (IVAP) to calibrate the probabilities associated with the output tokens corresponding to the binary labels.
  arXiv  Detail & Related papers  (2024-07-01T09:31:03Z)
• COBias and Debias: Minimizing Language Model Pairwise Accuracy Bias via Nonlinear Integer Programming [12.287692969438169]
  We tackle imbalance in per-class prediction accuracy by reconceptualizing it as the Con Oddity Bias (COBias)<n>We propose Debiasing Programming (DNIP) to correct ICL per-class probabilities towards lower COBias and higher overall accuracy.<n>DNIP simultaneously achieves significant COBias (-27%) and accuracy improvement (+12%) over the conventional ICL approach.
  arXiv  Detail & Related papers  (2024-05-13T10:30:33Z)
• Uncertainty-guided Boundary Learning for Imbalanced Social Event Detection [64.4350027428928]
  We propose a novel uncertainty-guided class imbalance learning framework for imbalanced social event detection tasks. Our model significantly improves social event representation and classification tasks in almost all classes, especially those uncertain ones.
  arXiv  Detail & Related papers  (2023-10-30T03:32:04Z)
• Deep Imbalanced Regression via Hierarchical Classification Adjustment [50.19438850112964]
  Regression tasks in computer vision are often formulated into classification by quantizing the target space into classes. The majority of training samples lie in a head range of target values, while a minority of samples span a usually larger tail range. We propose to construct hierarchical classifiers for solving imbalanced regression tasks. Our novel hierarchical classification adjustment (HCA) for imbalanced regression shows superior results on three diverse tasks.
  arXiv  Detail & Related papers  (2023-10-26T04:54:39Z)
• Boosting Fair Classifier Generalization through Adaptive Priority Reweighing [59.801444556074394]
  A performance-promising fair algorithm with better generalizability is needed. This paper proposes a novel adaptive reweighing method to eliminate the impact of the distribution shifts between training and test data on model generalizability.
  arXiv  Detail & Related papers  (2023-09-15T13:04:55Z)
• Revisiting adversarial training for the worst-performing class [60.231877895663956]
  There is a substantial gap between the top-performing and worst-performing classes in many datasets. We argue that this gap can be reduced by explicitly optimizing for the worst-performing class. Our method, called class focused online learning (CFOL), includes high probability convergence guarantees for the worst class loss.
  arXiv  Detail & Related papers  (2023-02-17T13:41:40Z)
• Efficient and Differentiable Conformal Prediction with General Function Classes [96.74055810115456]
  We propose a generalization of conformal prediction to multiple learnable parameters. We show that it achieves approximate valid population coverage and near-optimal efficiency within class. Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly.
  arXiv  Detail & Related papers  (2022-02-22T18:37:23Z)
• CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning [55.733193075728096]
  Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
  arXiv  Detail & Related papers  (2022-02-11T13:49:51Z)
• Learning Optimal Fair Classification Trees: Trade-offs Between Interpretability, Fairness, and Accuracy [7.215903549622416]
  We propose a mixed integer optimization framework for learning optimal classification trees. We benchmark our method against state-of-the-art approaches for fair classification on popular datasets. Our method consistently finds decisions with almost full parity, while other methods rarely do.
  arXiv  Detail & Related papers  (2022-01-24T19:47:10Z)
• The Interplay between Distribution Parameters and the Accuracy-Robustness Tradeoff in Classification [0.0]
  Adrial training tends to result in models that are less accurate on natural (unperturbed) examples compared to standard models. This can be attributed to either an algorithmic shortcoming or a fundamental property of the training data distribution. In this work, we focus on the latter case under a binary Gaussian mixture classification problem.
  arXiv  Detail & Related papers  (2021-07-01T06:57:50Z)
• PLM: Partial Label Masking for Imbalanced Multi-label Classification [59.68444804243782]
  Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.
  arXiv  Detail & Related papers  (2021-05-22T18:07:56Z)
• Deep F-measure Maximization for End-to-End Speech Understanding [52.36496114728355]
  We propose a differentiable approximation to the F-measure and train the network with this objective using standard backpropagation. We perform experiments on two standard fairness datasets, Adult, Communities and Crime, and also on speech-to-intent detection on the ATIS dataset and speech-to-image concept classification on the Speech-COCO dataset. In all four of these tasks, F-measure results in improved micro-F1 scores, with absolute improvements of up to 8% absolute, as compared to models trained with the cross-entropy loss function.
  arXiv  Detail & Related papers  (2020-08-08T03:02:27Z)
• VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning [38.33920705605981]
  We propose a method that can naturally incorporate class imbalance into the Active Learning framework. We show that our method can be applied to tasks classification on multiple different datasets.
  arXiv  Detail & Related papers  (2020-03-25T07:34:06Z)

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.