Related papers: Learning What to Fail On: Failure-Mode Contextual Bandits for Adversarial Data Curation

Learning What to Fail On: Failure-Mode Contextual Bandits for Adversarial Data Curation

URL: http://arxiv.org/abs/2608.18681v1
Date: Wed, 19 Aug 2026 08:31:15 GMT
Title: Learning What to Fail On: Failure-Mode Contextual Bandits for Adversarial Data Curation
Abstract summary: We introduce a failure-aware adversarial retrieval-augmented framework for improving robustness in natural language understanding.<n>Our approach improves RoBERTa-base accuracy from 88.48% to 92.60% on SNLI, from 75.04% to 80.95% on ANLI, and from 54.67% to 71.99% on MultiNLI.<n>We demonstrate transfer to FEVER fact verification, achieving up to 79.86% FEVER score and 82.45% accuracy with RoBERTa-large.
Score: 14.914697247710622
License: http://creativecommons.org/licenses/by/4.0/
Abstract: We introduce a failure-aware adversarial retrieval-augmented framework for improving robustness in natural language understanding. Rather than selecting synthetic examples with a fixed reward threshold, our method formulates adversarial data curation as a failure-mode contextual bandit problem. Candidate examples are generated with retrieval-augmented prompting, filtered by the current target model, automatically validated by an LLM judge ensemble, and clustered into recurring failure modes. A stochastic policy then selects which failure modes to sample for retraining, and is updated using validation-based reward that balances robustness gains, forgetting, and data cost. This makes the data curator itself the learning agent, enabling adaptive selection of the most useful model failures across training rounds. On standard benchmarks, our approach improves RoBERTa-base accuracy from 88.48% to 92.60% on SNLI, from 75.04% to 80.95% on ANLI, and from 54.67% to 71.99% on MultiNLI, while consistently outperforming prior adversarial augmentation methods. We further demonstrate transfer to FEVER fact verification, achieving up to 79.86\% FEVER score and 82.45\% accuracy with RoBERTa-large. Finally, we provide a theoretical interpretation showing that, under stated assumptions, failure-mode sampling can reduce shortcut-aligned gradient contributions while inducing bounded distributional drift. By combining retrieval, automated validation, contextual-bandit failure selection, and controlled adversarial retraining, our framework enables scalable robustness improvement without additional human annotation.

Related papers

Cross-Fitted Residual Utility for Primary-Preserving Cognitive Decision Correction in Automatic Modulation Classification [1.547549252134621]
We study a post-inference problem through cross-fitted residual utility and a primary-preserving cognitive decision policy.<n>A structured KAN-Fourier classifier supplies the default probability, while neural and non-neural candidates provide observable evidence.<n>On RMLA, RMLB, and HISAR, the complete system improves overall accuracy from 63.632% to 66.332%, 65.161% to 66.168%, and 77.769% to 79.867%.
arXiv Detail & Related papers (2026-08-03T11:07:37Z)
Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling [0.14323566945483493]
Modern preference alignment techniques, such as Best-of-N sampling, rely on reward models trained with pairwise comparison data.<n>We introduce a new data collection and modeling framework to address this critical reliability gap.<n>We show that when tuned as an alignment guardrail, it reduces reliability failures by 70%, and when tuned as an inference accelerator, it improves average inference speed by over 22%.
arXiv Detail & Related papers (2025-10-05T08:23:08Z)
Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment [16.352863226512984]
Test-time adaptation (TTA) enhances the zero-shot robustness under distribution shifts by leveraging unlabeled test data during inference.<n>Most methods rely on backpropagation or iterative optimization, which limits scalability and hinders real-time deployment.<n>We propose ADAPT, an Advanced Distribution-Aware and back propagation-free Test-time adaptation method.
arXiv Detail & Related papers (2025-08-21T13:42:49Z)
Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
arXiv Detail & Related papers (2024-03-01T03:27:08Z)
Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
arXiv Detail & Related papers (2023-12-27T09:03:43Z)
Binary Classification with Confidence Difference [100.08818204756093]
This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
arXiv Detail & Related papers (2023-10-09T11:44:50Z)
Robustness Evaluation and Adversarial Training of an Instance Segmentation Model [0.0]
We show that probabilisitic local equivalence is able to successfully distinguish between standardly-trained and adversarially-trained models. We show that probabilisitic local equivalence is able to successfully distinguish between standardly-trained and adversarially-trained models.
arXiv Detail & Related papers (2022-06-02T02:18:09Z)
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning [46.95063831057502]
We propose emphFreeMatch to define and adjust the confidence threshold in a self-adaptive manner according to the model's learning status. FreeMatch achieves textbf5.78%, textbf13.59%, and textbf1.28% error rate reduction over the latest state-of-the-art method FlexMatch on CIFAR-10 with 1 label per class.
arXiv Detail & Related papers (2022-05-15T10:07:52Z)
Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
arXiv Detail & Related papers (2022-01-11T23:01:12Z)
Adversarial Training with Rectified Rejection [114.83821848791206]
We propose to use true confidence (T-Con) as a certainty oracle, and learn to predict T-Con by rectifying confidence. We prove that under mild conditions, a rectified confidence (R-Con) rejector and a confidence rejector can be coupled to distinguish any wrongly classified input from correctly classified ones.
arXiv Detail & Related papers (2021-05-31T08:24:53Z)
Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
arXiv Detail & Related papers (2020-02-27T10:22:17Z)

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