Optimizing Class-Level Probability Reweighting Coefficients for Equitable Prompting Accuracy

• URL: http://arxiv.org/abs/2405.07623v8
• Date: Tue, 12 Aug 2025 14:44:44 GMT
• Title: Optimizing Class-Level Probability Reweighting Coefficients for Equitable Prompting Accuracy
• Authors: Ruixi Lin, Yang You,
• Abstract summary: LLMs often uncover biases from pre-training data's statistical regularities.<n>This leads to persistent, uneven class accuracy in classification and QA.<n>We develop a post-hoc probability reweighting method that directly optimize for non-differentiable performance-driven metrics.
• Score: 12.287692969438169
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Even as we engineer LLMs for alignment and safety, they often uncover biases from pre-training data's statistical regularities (from disproportionate co-occurrences to stereotypical associations mirroring human cognitive biases). This leads to persistent, uneven class accuracy in classification and QA. Such per-class accuracy disparities are not inherently resolved by architectural/training evolutions or data scaling, making post-hoc correction essential for equitable performance. To mitigate LLM class accuracy imbalance, we develop a post-hoc probability reweighting method that directly optimizes for non-differentiable performance-driven and fairness-aligned metrics, through a novel COBias metric that highlights disparities in class accuracies. This post-hoc bias mitigation method is grounded in discrete optimization with nonlinear integer programming (NIP) objectives and an efficient metaheuristic solution framework with theoretical convergence guarantees. Operating model-agnostically, it learns reweighting coefficients from output class probabilities to adjust LLM inference outputs without internal weight updates. Evaluations demonstrate its effectiveness: reducing COBias (61% relative reduction), increasing overall accuracy (18% relative increase), and achieving robust within-task generalization across diverse prompt configurations.

Related papers

• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Reducing Class-Wise Performance Disparity via Margin Regularization [82.81746960548382]
  Deep neural networks often exhibit substantial disparities in class-wise accuracy, even when trained on class-balanced data.<n>We present Margin Regularization for Performance Disparity Reduction (MR$2$), a theoretically principled regularization for classification.<n>Our analysis reveals how per-class feature variability contributes to error, motivating the use of larger margins for hard classes.
  arXiv  Detail & Related papers  (2026-01-30T12:56:08Z)
• Principled Algorithms for Optimizing Generalized Metrics in Binary Classification [53.604375124674796]
  We introduce principled algorithms for optimizing generalized metrics, supported by $H$-consistency and finite-sample generalization bounds.<n>Our approach reformulates metric optimization as a generalized cost-sensitive learning problem.<n>We develop new algorithms, METRO, with strong theoretical performance guarantees.
  arXiv  Detail & Related papers  (2025-12-29T01:33:42Z)
• Rebalancing with Calibrated Sub-classes (RCS): A Statistical Fusion-based Framework for Robust Imbalanced Classification across Modalities [16.993547305381327]
  Rebalancing with Calibrated Sub-classes (RCS) is a novel distribution calibration framework for robust imbalanced classification.<n>RCS fuses statistical information from the majority and intermediate class distributions via a weighted mixture of Gaussian components.
  arXiv  Detail & Related papers  (2025-10-10T00:06:13Z)
• CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment [7.702016079410588]
  We introduce CLUE (Calibration via Learning Uncertainty-Error Alignment), a novel approach that aligns predicted uncertainty with observed error during training.<n>We show that CLUE achieves superior calibration quality and competitive predictive performance with respect to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-05-28T19:23:47Z)
• 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.<n>We believe that the pursuit of overall accuracy should not come from enriching the strong classes, but from raising up the weak ones.<n>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)
• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.<n>Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• Let the Fuzzy Rule Speak: Enhancing In-context Learning Debiasing with Interpretability [12.287692969438169]
  Large language models (LLMs) often struggle with balanced class accuracy in text classification tasks using in-context learning (ICL) This paper delves deeper into the class accuracy imbalance issue, identifying that it arises because certain classes consistently receive disproportionately high ICL probabilities. We introduce FuRud, a method for sample-level class probability correction.
  arXiv  Detail & Related papers  (2024-12-26T01:56:42Z)
• Revisiting Essential and Nonessential Settings of Evidential Deep Learning [70.82728812001807]
  Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation. We propose Re-EDL, a simplified yet more effective variant of EDL.
  arXiv  Detail & Related papers  (2024-10-01T04:27:07Z)
• Covariance-corrected Whitening Alleviates Network Degeneration on Imbalanced Classification [6.197116272789107]
  Class imbalance is a critical issue in image classification that significantly affects the performance of deep recognition models. We propose a novel framework called Whitening-Net to mitigate the degenerate solutions. In scenarios with extreme class imbalance, the batch covariance statistic exhibits significant fluctuations, impeding the convergence of the whitening operation.
  arXiv  Detail & Related papers  (2024-08-30T10:49:33Z)
• Entropy Law: The Story Behind Data Compression and LLM Performance [115.70395740286422]
  We find that model performance is negatively correlated to the compression ratio of training data, which usually yields a lower training loss. Based on the findings of the entropy law, we propose a quite efficient and universal data selection method. We also present an interesting application of entropy law that can detect potential performance risks at the beginning of model training.
  arXiv  Detail & Related papers  (2024-07-09T08:14:29Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Preference Learning Algorithms Do Not Learn Preference Rankings [62.335733662381884]
  We study the conventional wisdom that preference learning trains models to assign higher likelihoods to more preferred outputs than less preferred outputs. We find that most state-of-the-art preference-tuned models achieve a ranking accuracy of less than 60% on common preference datasets.
  arXiv  Detail & Related papers  (2024-05-29T21:29:44Z)
• Teacher-Student Training for Debiasing: General Permutation Debiasing for Large Language Models [39.82130327284791]
  Large Language Models (LLMs) have demonstrated impressive zero-shot capabilities and versatility in NLP tasks. They sometimes fail to maintain crucial invariances for specific tasks. This paper addresses this inefficiency at inference time.
  arXiv  Detail & Related papers  (2024-03-20T13:38:07Z)
• Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models [7.089534153472173]
  We propose a null-input prompting method to calibrate intrinsic bias encoded in pre-trained language models. Our method significantly improves zero/few-shot learning performance of LMs for both in-context learning and prompt-based fine-tuning.
  arXiv  Detail & Related papers  (2024-02-15T22:54:24Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• Understanding the Detrimental Class-level Effects of Data Augmentation [63.1733767714073]
  achieving optimal average accuracy comes at the cost of significantly hurting individual class accuracy by as much as 20% on ImageNet. We present a framework for understanding how DA interacts with class-level learning dynamics. We show that simple class-conditional augmentation strategies improve performance on the negatively affected classes.
  arXiv  Detail & Related papers  (2023-12-07T18:37:43Z)
• Online Continual Learning via Logit Adjusted Softmax [24.327176079085703]
  Inter-class imbalance during training has been identified as a major cause of forgetting. We present a simple adjustment of model logits during training can effectively resist prior class bias. Our proposed method, Logit Adjusted Softmax, can mitigate the impact of inter-class imbalance not only in class-incremental but also in realistic general setups.
  arXiv  Detail & Related papers  (2023-11-11T03:03:33Z)
• Fine-tune Language Models to Approximate Unbiased In-context Learning [8.609157988755896]
  We introduce a reweighted algorithm called RICL (Reweighted In-context Learning) This algorithm fine-tunes language models using an unbiased validation set to determine the optimal weight for each input-output example. We also introduce a low-cost reweighted algorithm, a linear optimal weight approximation algorithm called LARICL.
  arXiv  Detail & Related papers  (2023-10-05T06:16:01Z)
• Semi-Supervised Learning with Multiple Imputations on Non-Random Missing Labels [0.0]
  Semi-Supervised Learning (SSL) is implemented when algorithms are trained on both labeled and unlabeled data. This paper proposes two new methods of combining multiple imputation models to achieve higher accuracy and less bias.
  arXiv  Detail & Related papers  (2023-08-15T04:09:53Z)
• Exploring Vision-Language Models for Imbalanced Learning [29.235472353759388]
  Vision-Language models (VLMs) that use contrastive language-image pre-training have shown promising zero-shot classification performance. Our study highlights the significance of imbalanced learning algorithms in face of VLMs pre-trained by huge data.
  arXiv  Detail & Related papers  (2023-04-04T01:56:16Z)
• CLIPood: Generalizing CLIP to Out-of-Distributions [73.86353105017076]
  Contrastive language-image pre-training (CLIP) models have shown impressive zero-shot ability, but the further adaptation of CLIP on downstream tasks undesirably degrades OOD performances. We propose CLIPood, a fine-tuning method that can adapt CLIP models to OOD situations where both domain shifts and open classes may occur on unseen test data. Experiments on diverse datasets with different OOD scenarios show that CLIPood consistently outperforms existing generalization techniques.
  arXiv  Detail & Related papers  (2023-02-02T04:27:54Z)
• Deep Negative Correlation Classification [82.45045814842595]
  Existing deep ensemble methods naively train many different models and then aggregate their predictions. We propose deep negative correlation classification (DNCC) DNCC yields a deep classification ensemble where the individual estimator is both accurate and negatively correlated.
  arXiv  Detail & Related papers  (2022-12-14T07:35:20Z)
• An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning [103.65758569417702]
  Semi-supervised learning (SSL) has shown great promise in leveraging unlabeled data to improve model performance. We consider a more realistic and challenging setting called imbalanced SSL, where imbalanced class distributions occur in both labeled and unlabeled data. We study a simple yet overlooked baseline -- SimiS -- which tackles data imbalance by simply supplementing labeled data with pseudo-labels.
  arXiv  Detail & Related papers  (2022-11-20T21:18:41Z)
• Oracle Inequalities for Model Selection in Offline Reinforcement Learning [105.74139523696284]
  We study the problem of model selection in offline RL with value function approximation. We propose the first model selection algorithm for offline RL that achieves minimax rate-optimal inequalities up to logarithmic factors. We conclude with several numerical simulations showing it is capable of reliably selecting a good model class.
  arXiv  Detail & Related papers  (2022-11-03T17:32:34Z)
• Learnable Distribution Calibration for Few-Shot Class-Incremental Learning [122.2241120474278]
  Few-shot class-incremental learning (FSCIL) faces challenges of memorizing old class distributions and estimating new class distributions given few training samples. We propose a learnable distribution calibration (LDC) approach, with the aim to systematically solve these two challenges using a unified framework.
  arXiv  Detail & Related papers  (2022-10-01T09:40:26Z)
• Fairly Accurate: Learning Optimal Accuracy vs. Fairness Tradeoffs for Hate Speech Detection [8.841221697099687]
  We introduce a differentiable measure that enables direct optimization of group fairness in model training. We evaluate our methods on the specific task of hate speech detection. Empirical results across convolutional, sequential, and transformer-based neural architectures show superior empirical accuracy vs. fairness trade-offs over prior work.
  arXiv  Detail & Related papers  (2022-04-15T22:11:25Z)
• A Gating Model for Bias Calibration in Generalized Zero-shot Learning [18.32369721322249]
  Generalized zero-shot learning (GZSL) aims at training a model that can generalize to unseen class data by only using auxiliary information. One of the main challenges in GZSL is a biased model prediction toward seen classes caused by overfitting on only available seen class data during training. We propose a two-stream autoencoder-based gating model for GZSL.
  arXiv  Detail & Related papers  (2022-03-08T16:41:06Z)
• FORML: Learning to Reweight Data for Fairness [2.105564340986074]
  We introduce Fairness Optimized Reweighting via Meta-Learning (FORML) FORML balances fairness constraints and accuracy by jointly optimizing training sample weights and a neural network's parameters. We show that FORML improves equality of opportunity fairness criteria over existing state-of-the-art reweighting methods by approximately 1% on image classification tasks and by approximately 5% on a face prediction task.
  arXiv  Detail & Related papers  (2022-02-03T17:36:07Z)
• 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)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)
• Generalized Zero-Shot Learning Via Over-Complete Distribution [79.5140590952889]
  We propose to generate an Over-Complete Distribution (OCD) using Conditional Variational Autoencoder (CVAE) of both seen and unseen classes. The effectiveness of the framework is evaluated using both Zero-Shot Learning and Generalized Zero-Shot Learning protocols.
  arXiv  Detail & Related papers  (2020-04-01T19:05:28Z)

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.