Related papers: Controlling Learned Effects to Reduce Spurious Cor…
Neural networks often exhibit simplicity bias, favoring simpler features over more complex ones, even when both are equally predictive. We introduce a novel method called imbalanced label coupling to explore and extend this simplicity bias…
In recent years, research on learning with noisy labels has focused on devising novel algorithms that can achieve robustness to noisy training labels while generalizing to clean data. These algorithms often incorporate sophisticated…
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a…
Conformal Prediction (CP) controls the prediction uncertainty of classification systems by producing a small prediction set, ensuring a predetermined probability that the true class lies within this set. This is commonly done by defining a…
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…
Partial label learning (PLL) aims to solve the problem where each training instance is associated with a set of candidate labels, one of which is the correct label. Most PLL algorithms try to disambiguate the candidate label set, by either…
Preference-based reinforcement learning (PbRL) promises to learn a complex reward function with binary human preference. However, such human-in-the-loop formulation requires considerable human effort to assign preference labels to segment…
Various natural language processing tasks are structured prediction problems where outputs are constructed with multiple interdependent decisions. Past work has shown that domain knowledge, framed as constraints over the output space, can…
We study attribute control in language models through the method of Causal Average Treatment Effect (Causal ATE). Existing methods for the attribute control task in Language Models (LMs) check for the co-occurrence of words in a sentence…
Soft augmentation regularizes the supervised learning process of image classifiers by reducing label confidence of a training sample based on the magnitude of random-crop augmentation applied to it. This paper extends this adaptive label…
We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. Given a training corpus and control criteria formulated as a sequence-level constraint on model outputs, our method fine-tunes the…
Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…
Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks. In this work, we aim to answer the following research question: Can we reduce spurious…
Most NLP datasets are manually labeled, so suffer from inconsistent labeling or limited size. We propose methods for automatically improving datasets by viewing them as graphs with expected semantic properties. We construct a paraphrase…
We propose a novel sample selection method for image classification in the presence of noisy labels. Existing methods typically consider small-loss samples as correctly labeled. However, some correctly labeled samples are inherently…
In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…
Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While…
A major challenge to out-of-distribution generalization is reliance on spurious features -- patterns that are predictive of the class label in the training data distribution, but not causally related to the target. Standard methods for…
Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…
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,…