相关论文: CORE: A Retrieve-then-Edit Framework for Counterfa…

Recent advancements in generative AI have introduced novel prospects and practical implementations. Especially diffusion models show their strength in generating diverse and, at the same time, realistic features, positioning them well for…

Counterfactual explanation methods interpret the outputs of a machine learning model in the form of "what-if scenarios" without compromising the fidelity-interpretability trade-off. They explain how to obtain a desired prediction from the…

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against…

Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However,…

While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using…

Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?". The comparison of this instance before and after…

This paper tackles the problem of time-to-event counterfactual survival prediction, aiming to optimize individualized survival outcomes in the presence of heterogeneity and censored data. We propose CURE, a framework that advances…

Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is a…

Large language models (LLMs) often solve challenging math exercises yet fail to apply the concept right when the problem requires genuine understanding. Popular Reinforcement Learning with Verifiable Rewards (RLVR) pipelines reinforce final…

Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning. In general, a keyword is regarded as a shortcut if it creates a…

Causal reasoning and logical reasoning are two important types of reasoning abilities for human intelligence. However, their relationship has not been extensively explored under machine intelligence context. In this paper, we explore how…

Counterfactual explanations provide ways of achieving a favorable model outcome with minimum input perturbation. However, counterfactual explanations can also be leveraged to reconstruct the model by strategically training a surrogate model…

Imitation learning in robotics faces significant challenges in generalization due to the complexity of robotic environments and the high cost of data collection. We introduce RoCoDA, a novel method that unifies the concepts of invariance,…

Recent literature focuses on utilizing the entity information in the sentence-level relation extraction (RE), but this risks leaking superficial and spurious clues of relations. As a result, RE still suffers from unintended entity bias,…

A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples…

Standard decoding in Masked Diffusion Models (MDMs) is hindered by context rigidity: tokens are retained based on transient high confidence, often ignoring that early predictions lack full context. This creates cascade effects where initial…

Efficient access to high-quality information is vital for online platforms. To promote more useful information, users not only create new content but also evaluate existing content, often through helpfulness voting. Although aggregated…

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retrieved documents…

Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems. In computer vision applications, generative counterfactual…

Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information. Existing approaches either rely on expensive supervised fine-tuning to generate…