Related papers: Dual Debiasing for Noisy In-Context Learning for T…
In-context learning (ICL) is an important yet not fully understood ability of pre-trained large language models (LLMs). It can greatly enhance task performance using a few examples, termed demonstrations, without fine-tuning. Although…
Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…
Instruction-guided text-to-speech (TTS) research has reached a maturity level where excellent speech generation quality is possible on demand, yet two coupled biases persist in reducing perceived quality: accent bias, where models default…
Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…
Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could…
Morality plays an important role in culture, identity, and emotion. Recent advances in natural language processing have shown that it is possible to classify moral values expressed in text at scale. Morality classification relies on human…
Recently, deep learning models have been widely applied in program understanding tasks, and these models achieve state-of-the-art results on many benchmark datasets. A major challenge of deep learning for program understanding is that the…
Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or…
Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While recent approaches have extended the context windows of LLMs…
Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…
In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a…
Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information…
Several works in computer vision have demonstrated the effectiveness of active learning for adapting the recognition model when new unlabeled data becomes available. Most of these works consider that labels obtained from the annotator are…
Noise in data appears to be inevitable in most real-world machine learning applications and would cause severe overfitting problems. Not only can data features contain noise, but labels are also prone to be noisy due to human input. In this…
Learning from noisy data has attracted much attention, where most methods focus on closed-set label noise. However, a more common scenario in the real world is the presence of both open-set and closed-set noise. Existing methods typically…
We introduce a dataset of concept learning tasks that helps uncover implicit biases in large language models. Using in-context concept learning experiments, we found that language models may have a bias toward upward monotonicity in…
In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a…
Previous studies have found that PLM-based retrieval models exhibit a preference for LLM-generated content, assigning higher relevance scores to these documents even when their semantic quality is comparable to human-written ones. This…
For high-resource languages like English, text classification is a well-studied task. The performance of modern NLP models easily achieves an accuracy of more than 90% in many standard datasets for text classification in English (Xie et…
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,…