Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation

In current visual model training, models often rely on only limited sufficient causes for their predictions, which makes them sensitive to distribution shifts or the absence of key features. Attribution methods can accurately identify a model's critical regions. However, masking these areas to create counterfactuals often causes the model to misclassify the target, while humans can still easily recognize it. This divergence highlights that the model's learned dependencies may not be sufficiently causal. To address this issue, we propose Subset-Selected Counterfactual Augmentation (SS-CA), which integrates counterfactual explanations directly into the training process for targeted intervention. Building on the subset-selection-based LIMA attribution method, we develop Counterfactual LIMA to identify minimal spatial region sets whose removal can selectively alter model predictions. Leveraging these attributions, we introduce a data augmentation strategy that replaces the identified regions with natural background, and we train the model jointly on both augmented and original samples to mitigate incomplete causal learning. Extensive experiments across multiple ImageNet variants show that SS-CA improves generalization on in-distribution (ID) test data and achieves superior performance on out-of-distribution (OOD) benchmarks such as ImageNet-R and ImageNet-S. Under perturbations including noise, models trained with SS-CA also exhibit enhanced generalization, demonstrating that our approach effectively uses interpretability insights to correct model deficiencies and improve both performance and robustness.

RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline

If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself freely reproduces the target content. As such, we propose RECAP, an agentic pipeline designed to elicit and verify memorized training data from LLM outputs. At the heart of RECAP is a feedback-driven loop, where an initial extraction attempt is evaluated by a secondary language model, which compares the output against a reference passage and identifies discrepancies. These are then translated into minimal correction hints, which are fed back into the target model to guide subsequent generations. In addition, to address alignment-induced refusals, RECAP includes a jailbreaking module that detects and overcomes such barriers. We evaluate RECAP on EchoTrace, a new benchmark spanning over 30 full books, and the results show that RECAP leads to substantial gains over single-iteration approaches. For instance, with GPT-4.1, the average ROUGE-L score for the copyrighted text extraction improved from 0.38 to 0.47 - a nearly 24% increase.

Modeling e-Learners' Cognitive and Metacognitive Strategy in Comparative Question Solving

Cognitive and metacognitive strategy had demonstrated a significant role in self-regulated learning (SRL), and an appropriate use of strategies is beneficial to effective learning or question-solving tasks during a human-computer interaction process. This paper proposes a novel method combining Knowledge Map (KM) based data mining technique with Thinking Map (TM) to detect learner's cognitive and metacognitive strategy in the question-solving scenario. In particular, a graph-based mining algorithm is designed to facilitate our proposed method, which can automatically map cognitive strategy to metacognitive strategy with raising abstraction level, and make the cognitive and metacognitive process viewable, which acts like a reverse engineering engine to explain how a learner thinks when solving a question. Additionally, we develop an online learning environment system for participants to learn and record their behaviors. To corroborate the effectiveness of our approach and algorithm, we conduct experiments recruiting 173 postgraduate and undergraduate students, and they were asked to complete a question-solving task, such as "What are similarities and differences between array and pointer?" from "The C Programming Language" course and "What are similarities and differences between packet switching and circuit switching?" from "Computer Network Principle" course. The mined strategies patterns results are encouraging and supported well our proposed method.