SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification

• URL: http://arxiv.org/abs/2506.14587v2
• Date: Sat, 21 Jun 2025 16:12:29 GMT
• Title: SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification
• Abstract summary: Shortcut learning undermines model generalization to out-of-distribution data.<n>We propose SCISSOR (Semantic Cluster Intervention for Suppressing ShORtcut), a network-based debiasing approach.<n>We evaluate SCISSOR on 6 models across 4 benchmarks: Chest-XRay and Not-MNIST in computer vision, and GYAFC and Yelp in NLP tasks.
• Score: 16.633948320306832
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Shortcut learning undermines model generalization to out-of-distribution data. While the literature attributes shortcuts to biases in superficial features, we show that imbalances in the semantic distribution of sample embeddings induce spurious semantic correlations, compromising model robustness. To address this issue, we propose SCISSOR (Semantic Cluster Intervention for Suppressing ShORtcut), a Siamese network-based debiasing approach that remaps the semantic space by discouraging latent clusters exploited as shortcuts. Unlike prior data-debiasing approaches, SCISSOR eliminates the need for data augmentation and rewriting. We evaluate SCISSOR on 6 models across 4 benchmarks: Chest-XRay and Not-MNIST in computer vision, and GYAFC and Yelp in NLP tasks. Compared to several baselines, SCISSOR reports +5.3 absolute points in F1 score on GYAFC, +7.3 on Yelp, +7.7 on Chest-XRay, and +1 on Not-MNIST. SCISSOR is also highly advantageous for lightweight models with ~9.5% improvement on F1 for ViT on computer vision datasets and ~11.9% for BERT on NLP. Our study redefines the landscape of model generalization by addressing overlooked semantic biases, establishing SCISSOR as a foundational framework for mitigating shortcut learning and fostering more robust, bias-resistant AI systems.

Related papers

• Adversarial LassoNet: Robust Feature Selection via Stability-Driven Sparse Learning [9.282673102334869]
  AdLNet is a stability-driven sparse feature selection framework that integrates input-space adversarial perturbations with the hierarchical sparsity mechanism of LassoNet.<n> Experiments show that AdLNet maintains competitive sparse-selection performance while improving out-of-distribution robustness by 4.4% and feature support by 6.3% under nearly matched support sparsity on ColoredMNIST.
  arXiv  Detail & Related papers  (2026-07-04T12:01:53Z)
• Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models [0.0]
  Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving mathematical reasoning in language models.<n>We systematically compare five reward conditions applied to Qwen2.5-0.5B fine-tuned with Group Relative Policy Optimization (GRPO) on GSM8K.<n>Our results demonstrate that reward derivation is a first-order design decision for RLVR, with process-level supervision substantially improving both accuracy and trace fidelity in small language models.
  arXiv  Detail & Related papers  (2026-07-03T02:16:06Z)
• Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning [56.48520300004217]
  We present Seirnes, a self-play RL framework that transforms contextual interference into an internal training signal.<n>A single model is trained to both construct plausible yet distracting contexts that expose its own reasoning blind spots.<n>By pitting these competing objectives against each other, Seirnes compels the model to move beyond superficial pattern matching.
  arXiv  Detail & Related papers  (2026-05-12T06:58:35Z)
• WaferSAGE: Large Language Model-Powered Wafer Defect Analysis via Synthetic Data Generation and Rubric-Guided Reinforcement Learning [8.029209745978878]
  We present WaferSAGE, a framework for wafer defect visual question answering using small vision-language models.<n>We employ clustering-based cleaning to filter label noise, then generate comprehensive defect descriptions using vision-language models.<n>These rubrics guide the synthesis of VQA pairs, ensuring coverage across defect type identification, spatial distribution, morphology, and root cause analysis.
  arXiv  Detail & Related papers  (2026-04-30T09:19:26Z)
• SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models [36.40093869747498]
  We propose Sparse Embedding Modulation (SEM), a post-hoc, zero-shot debiasing framework that operates in a Sparse Autoencoder latent space.<n>SEM identifies and modulates bias-relevant neurons while preserving query-relevant ones.<n>Our results demonstrate that sparse latent representations provide an effective foundation for post-hoc debiasing of vision-language models.
  arXiv  Detail & Related papers  (2026-03-19T15:28:08Z)
• Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models [50.99097734404912]
  We show that RL-friendly models exhibit intra-class compactness and inter-class separation in their probability assignments to correct vs. incorrect responses.<n>Experiments across six mathematical benchmarks show consistent improvements across all model families, with gains up to 5.9 points on AIME24.
  arXiv  Detail & Related papers  (2026-01-11T13:34:44Z)
• ANROT-HELANet: Adverserially and Naturally Robust Attention-Based Aggregation Network via The Hellinger Distance for Few-Shot Classification [4.283774189998499]
  We introduce ANROT-HELANet, an Adversarially and Naturally RObusT Hellinger Aggregation Network.<n>Our approach implements an adversarially and naturally robust Hellinger distance-based feature class aggregation scheme.<n>Our approach achieves superior image reconstruction quality with a FID score of 2.75, outperforming traditional VAE (3.43) and WAE (3.38) approaches.
  arXiv  Detail & Related papers  (2025-09-14T11:44:43Z)
• Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems [3.215065407261898]
  Multi-agent systems that combine large language models with external tools are rapidly transitioning from research laboratories into high-stakes domains.<n>This "Advanced" sequel fills that gap by providing an algorithmic instantiation or empirical evidence.<n>AMDM cuts anomaly-detection latency from 12.3 s to 5.6 s on simulated goal drift and reduces false-positive rates from 4.5% to 0.9%.
  arXiv  Detail & Related papers  (2025-08-28T15:52:49Z)
• SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation [38.37231157929935]
  Monte Carlo Tree Search is a powerful technique for generating high-quality chain-of-thought data.<n> conventional approaches typically retain only the top-scoring trajectory from the search tree.<n>We propose SIGMA, a novel framework that reintegrates these discarded sibling nodes to refine LLM reasoning.
  arXiv  Detail & Related papers  (2025-06-06T18:55:16Z)
• Interpretable Few-Shot Image Classification via Prototypical Concept-Guided Mixture of LoRA Experts [79.18608192761512]
  Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable.<n>We propose a Few-Shot Prototypical Concept Classification framework that mitigates two key challenges under low-data regimes: parametric imbalance and representation misalignment.<n>Our approach consistently outperforms existing SEMs by a notable margin, with 4.2%-8.7% relative gains in 5-way 5-shot classification.
  arXiv  Detail & Related papers  (2025-06-05T06:39:43Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data.<n>These findings highlight the reliance on recall over rigorous logical inference.<n>This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• Entanglement Classification of Arbitrary Three-Qubit States via Artificial Neural Networks [2.715284063484557]
  We design and implement artificial neural networks (ANNs) to detect and classify entanglement for three-qubit systems. The models are trained and validated on a simulated dataset of randomly generated states. Remarkably, we find that feeding only 7 diagonal elements of the density matrix into the ANN results in an accuracy greater than 94% for both tasks.
  arXiv  Detail & Related papers  (2024-11-18T06:50:10Z)
• An Augmentation-based Model Re-adaptation Framework for Robust Image Segmentation [0.799543372823325]
  We propose an Augmentation-based Model Re-adaptation Framework (AMRF) to enhance the generalisation of segmentation models. By observing segmentation masks from conventional models (FCN and U-Net) and a pre-trained SAM model, we determine a minimal augmentation set that optimally balances training efficiency and model performance. Our results demonstrate that the fine-tuned FCN surpasses its baseline by 3.29% and 3.02% in cropping accuracy, and 5.27% and 4.04% in classification accuracy on two temporally continuous datasets.
  arXiv  Detail & Related papers  (2024-09-14T21:01:49Z)
• Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study [61.65123150513683]
  multimodal foundation models, such as CLIP, produce state-of-the-art zero-shot results. It is reported that these models close the robustness gap by matching the performance of supervised models trained on ImageNet. We show that CLIP leads to a significant robustness drop compared to supervised ImageNet models on our benchmark.
  arXiv  Detail & Related papers  (2024-03-15T17:33:49Z)
• Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization [64.36097398869774]
  Semi-supervised learning (SSL) has been an active research topic for large-scale 3D scene understanding. The existing SSL-based methods suffer from severe training bias due to class imbalance and long-tail distributions of the point cloud data. We introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively.
  arXiv  Detail & Related papers  (2024-01-13T04:16:40Z)
• Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models [75.9543301303586]
  Foundation models like CLIP allow zero-shot transfer on various tasks without additional training data. Fine-tuning and ensembling are also commonly adopted to better fit the downstream tasks. However, we argue that prior work has overlooked the inherent biases in foundation models.
  arXiv  Detail & Related papers  (2023-10-12T08:01:11Z)
• Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing [72.14557106085284]
  slice detection models (SDM) automatically identify underperforming groups of datapoints. This paper proposes a benchmark named "Discover, Explain, improve (DEIM)" for classification NLP tasks. Our evaluation shows that Edisa can accurately select error-prone datapoints with informative semantic features.
  arXiv  Detail & Related papers  (2022-11-08T19:00:00Z)
• Improved Aggregating and Accelerating Training Methods for Spatial Graph Neural Networks on Fraud Detection [0.0]
  This work proposes an improved deep architecture to extend CAmouflage-REsistant GNN (CARE-GNN) to deep models named as Residual Layered CARE-GNN (RLC-GNN) Three issues of RLC-GNN are the usage of neighboring information reaching limitation, the training difficulty and lack of comprehensive consideration about node features and external patterns. Experiments are conducted on Yelp and Amazon datasets.
  arXiv  Detail & Related papers  (2022-02-14T09:51:35Z)
• Consistency and Monotonicity Regularization for Neural Knowledge Tracing [50.92661409499299]
  Knowledge Tracing (KT) tracking a human's knowledge acquisition is a central component in online learning and AI in Education. We propose three types of novel data augmentation, coined replacement, insertion, and deletion, along with corresponding regularization losses. Extensive experiments on various KT benchmarks show that our regularization scheme consistently improves the model performances.
  arXiv  Detail & Related papers  (2021-05-03T02:36:29Z)

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.