Improving Model Safety by Targeted Error Correction

• URL: http://arxiv.org/abs/2605.02544v1
• Date: Mon, 04 May 2026 12:47:41 GMT
• Title: Improving Model Safety by Targeted Error Correction
• Abstract summary: We introduce a dual-classifier GBDT pipeline to distinguish human-like errors from high-risk non-human misclassifications.<n>Our results confirm the pipeline introduces negligible inference (1.60% overhead for the animal dataset, 1.84% for ISIC, and 1.70% for SICAPv2)<n>Our conservative correction strategy successfully reduced dangerous nonhuman errors by 34.1% in ISIC and 12.57% in SICAPv2.
• Score: 10.82789277277678
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The widespread adoption of machine learning in critical applications demands techniques to mitigate high-consequence errors. Our method utilizes a dual-classifier GBDT pipeline to distinguish routine human-like errors from high-risk non-human misclassifications. Evaluated across three domains, animal breed classification, skin lesion diagnosis (ISIC 2018), and prostate histopathology (SICAPv2), our framework demonstrates robust safety improvements. To address real-world deployment concerns, our results confirm the pipeline introduces negligible inference latency (1.60% overhead for the animal dataset, 1.84% for ISIC, and 1.70% for SICAPv2) while outperforming traditional Maximum Class Probability (MCP) baselines in correction precision. Our conservative correction strategy successfully reduced dangerous non-human errors by 34.1% in ISIC and 12.57% in SICAPv2, improving super-class diagnostic safety to 90.41% and 92.13% respectively. This proves that safety-critical reliability can be substantially enhanced post-hoc without expensive model retraining. keywords: Error Analysis, Post-hoc Correction, Trustworthy AI.

Related papers

• FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation [40.53898394579726]
  FORCE is a 3-stage framework that stabilizes fine-tuning by tackling both issues.<n>FORCE achieves a 79% absolute improvement in success rates and outperform prior RL methods by 10%, while accelerating training by 32.5%.
  arXiv  Detail & Related papers  (2026-06-24T16:23:18Z)
• Safety and accuracy follow different scaling laws in clinical large language models [4.212844425331427]
  RadSaFE-200 is a benchmark of 200 multiple-choice questions with clinician-defined clean evidence, conflict evidence, and option-level labels for high-risk error, unsafe answer, and evidence contradiction.<n>Clean evidence produced the strongest improvement, increasing mean accuracy from 73.5% to 94.1%, while reducing high-risk error from 12.0% to 2.6%.<n>Standard RAG and agentic RAG did not reproduce this safety profile, but high-risk error and dangerous overconfidence remained elevated.
  arXiv  Detail & Related papers  (2026-05-05T17:57:19Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• Severe Domain Shift in Skeleton-Based Action Recognition:A Study of Uncertainty Failure in Real-World Gym Environments [0.0]
  We present a systematic study of a severe domain shift using a novel Gym2D dataset and the UCF101 dataset.<n>Our work challenges standard deployment assumptions, providing a principled safety analysis of both semantic and geometric skeleton recognition deployment.
  arXiv  Detail & Related papers  (2026-03-16T17:37:17Z)
• When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models [54.08784776767683]
  We present Physical-Conditioned World Model Attack (PhysCond-WMA), the first white-box world model attack that perturbs physical-condition channels.<n>PhysCond-WMA induces semantic, logic, or decision-level distortion while preserving perceptual fidelity.
  arXiv  Detail & Related papers  (2026-02-21T07:22:37Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Optimization Instability in Autonomous Agentic Workflows for Clinical Symptom Detection [3.0950658457067433]
  We investigate a phenomenon in which continued autonomous improvement paradoxically degrades classifier performance.<n>We observed that validation sensitivity oscillated between 1.0 and 0.0 across iterations, with severity inversely proportional to class prevalence.<n>With selector agent oversight, the system outperformed expert-curated lexicons on brain fog detection by 331% (F1) and chest pain by 7%, despite requiring only a single natural language term as input.
  arXiv  Detail & Related papers  (2026-02-17T21:45:20Z)
• Temperature Scaling Attack Disrupting Model Confidence in Federated Learning [4.863985119779627]
  We present the Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy.<n>Our results establish calibration integrity as a critical attack surface in federated learning.
  arXiv  Detail & Related papers  (2026-02-06T12:01:54Z)
• Powerful Training-Free Membership Inference Against Autoregressive Language Models [3.9380576851378657]
  We present EZ-MIA, a membership inference attack that exploits a key observation: memorization manifests most strongly at error positions.<n>We introduce the Error Zone (EZ) score, which measures the directional imbalance of probability shifts at error positions.<n>Results establish that privacy risks of fine-tuned language models are substantially greater than previously understood.
  arXiv  Detail & Related papers  (2026-01-17T16:59:41Z)
• Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty [48.593888815135934]
  Large Language Models (LLMs) are increasingly important for safe deployment in high-stakes domains.<n>Existing recovery methods rely on data-intensive global parameter adjustments, implicitly assuming that SFT deeply corrupts the models' ability to recognize their knowledge boundaries.<n>We propose Honesty-Critical Neurons Restoration (HCNR) to surgically repair this suppressed capacity.
  arXiv  Detail & Related papers  (2025-11-17T05:30:48Z)
• ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal [27.26251627767238]
  Large Language Models (LLMs) increasingly exhibit over-refusal - erroneously rejecting benign queries due to overly conservative safety measures.<n>This paper introduces the first evolutionary testing framework, ORFuzz, for the systematic detection and analysis of LLM over-refusals.
  arXiv  Detail & Related papers  (2025-08-15T05:03:26Z)
• Accurate and Reliable Predictions with Mutual-Transport Ensemble [46.368395985214875]
  We propose a co-trained auxiliary model and adaptively regularizes the cross-entropy loss using Kullback-Leibler (KL) We show that MTE can simultaneously enhance both accuracy and uncertainty calibration. For example, on the CIFAR-100 dataset, our MTE method on ResNet34/50 achieved significant improvements compared to previous state-of-the-art method.
  arXiv  Detail & Related papers  (2024-05-30T03:15:59Z)
• (Certified!!) Adversarial Robustness for Free! [116.6052628829344]
  We certify 71% accuracy on ImageNet under adversarial perturbations constrained to be within a 2-norm of 0.5. We obtain these results using only pretrained diffusion models and image classifiers, without requiring any fine tuning or retraining of model parameters.
  arXiv  Detail & Related papers  (2022-06-21T17:27:27Z)

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.