相关论文: Unveiling Project-Specific Bias in Neural Code Mod…

While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their…

Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize are not well understood yet. When class labels in the…

The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approaches based on state-of-the-art model architectures. Nevertheless, we believe that the current…

The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize…

In-context learning (ICL) is an important paradigm for adapting large language models (LLMs) to new tasks, but the generalization behavior of ICL remains poorly understood. We investigate the inductive biases of ICL from the perspective of…

Traditional machine learning paradigms are based on the assumption that both training and test data follow the same statistical pattern, which is mathematically referred to as Independent and Identically Distributed ($i.i.d.$). However, in…

Existing works show that although modern neural networks achieve remarkable generalization performance on the in-distribution (ID) dataset, the accuracy drops significantly on the out-of-distribution (OOD) datasets \cite{recht2018cifar,…

The advent of large language models (LLMs) has enabled significant performance gains in the field of natural language processing. However, recent studies have found that LLMs often resort to shortcuts when performing tasks, creating an…

In the real world, a learning system could receive an input that is unlike anything it has seen during training. Unfortunately, out-of-distribution samples can lead to unpredictable behaviour. We need to know whether any given input belongs…

Machine learning models, while progressively advanced, rely heavily on the IID assumption, which is often unfulfilled in practice due to inevitable distribution shifts. This renders them susceptible and untrustworthy for deployment in…

While deep learning models excel at predictive tasks, they often overfit due to their complex structure and large number of parameters, causing them to memorize training data, including noise, rather than learn patterns that generalize to…

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…

Drawing on constructs from psychology, prior work has identified a distinction between explicit and implicit bias in large language models (LLMs). While many LLMs undergo post-training alignment and safety procedures to avoid expressions of…

Generative Large Language Models (LLMs) are capable of being in-context learners. However, the underlying mechanism of in-context learning (ICL) is still a major research question, and experimental research results about how models exploit…

Meta-learning that uses implicit gradient have provided an exciting alternative to standard techniques which depend on the trajectory of the inner loop training. Implicit meta-learning (IML), however, require computing $2^{nd}$ order…

Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test. Recent work on…

Data augmentation is used in machine learning to make the classifier invariant to label-preserving transformations. Usually this invariance is only encouraged implicitly by including a single augmented input during training. However,…

Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. However, the likelihood, a measure of LLM's plausibility for a sentence, can vary due to superficial differences in sentences,…

It's better to say "I can't answer" than to answer incorrectly. This selective prediction ability is crucial for NLP systems to be reliably deployed in real-world applications. Prior work has shown that existing selective prediction…

Neural networks often make predictions relying on the spurious correlations from the datasets rather than the intrinsic properties of the task of interest, facing sharp degradation on out-of-distribution (OOD) test data. Existing de-bias…