相关论文: Data Augmentations for Improved (Large) Language M…

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…

Counterfactual learning from observational data involves learning a classifier on an entire population based on data that is observed conditioned on a selection policy. This work considers this problem in an active setting, where the…

Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of the pre-training corpus, or because synthetized data is used as a replacement for expensive…

Large models, encompassing large language and diffusion models, have shown exceptional promise in approximating human-level intelligence, garnering significant interest from both academic and industrial spheres. However, the training of…

Counterfactual examples for an input -- perturbations that change specific features but not others -- have been shown to be useful for evaluating bias of machine learning models, e.g., against specific demographic groups. However,…

A major impediment to the application of deep learning to real-world problems is the scarcity of labeled data. Small training sets are in fact of no use to deep networks as, due to the large number of trainable parameters, they will very…

Large language models (LLMs) play a crucial role in natural language processing (NLP) tasks, improving the understanding, generation, and manipulation of human language across domains such as translating, summarizing, and classifying text.…

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…

As the significance of understanding the cause-and-effect relationships among variables increases in the development of modern systems and algorithms, learning causality from observational data has become a preferred and efficient approach…

Large language models (LLMs) can be used to generate text data for training and evaluating other models. However, creating high-quality datasets with LLMs can be challenging. In this work, we explore human-AI partnerships to facilitate high…

While counterfactual data augmentation offers a promising step towards robust generalization in natural language processing, producing a set of counterfactuals that offer valuable inductive bias for models remains a challenge. Most existing…

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings…

The spread of fake news harms individuals and presents a critical social challenge that must be addressed. Although numerous algorithmic and insightful features have been developed to detect fake news, many of these features can be…

Training and fine-tuning deep learning models, especially large language models (LLMs), on limited and imbalanced datasets poses substantial challenges. These issues often result in poor generalization, where models overfit to dominant…

Deep learning models are known to often learn features that spuriously correlate with the class label during training but are irrelevant to the prediction task. Existing methods typically address this issue by annotating potential spurious…

Using large training datasets enhances the generalization capabilities of neural networks. Semi-supervised learning (SSL) is useful when there are few labeled data and a lot of unlabeled data. SSL methods that use data augmentation are most…

The use of Large Language Models (LLMs) for simulating user behavior in the domain of Interactive Information Retrieval has recently gained significant popularity. However, their application and capabilities remain highly debated and…

Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

Given the rise of conflicts on social media, effective classification models to detect harmful behaviours are essential. Following the garbage-in-garbage-out maxim, machine learning performance depends heavily on training data quality.…