相关论文: Mind the Trade-off: Debiasing NLU Models without D…

Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a…

Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels. While many research works do not pay much attention to this fact, several recent efforts have been made to acknowledge and embrace the existence of…

Feedback Alignment (FA) methods are biologically inspired local learning rules for training neural networks with reduced communication between layers. While FA has potential applications in distributed and privacy-aware ML, limitations in…

Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in…

Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid…

Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD)…

Policy loss estimation remains a fundamental and long-standing challenge in reinforcement learning (RL) for diffusion language models (dLLMs). We introduce Reinforcement Learning from Denoising Feedback (RLDF), a novel training paradigm…

Adversarial examples are inputs to machine learning models designed to cause the model to make a mistake. They are useful for understanding the shortcomings of machine learning models, interpreting their results, and for regularisation. In…

Large language models (LLMs) often struggle with balanced class accuracy in text classification tasks using in-context learning (ICL), hindering some practical uses due to user dissatisfaction or safety risks caused by misclassifications.…

Existing debiasing methods inevitably make unreasonable or undesired predictions as they are designated and evaluated to achieve parity across different social groups but leave aside individual facts, resulting in modified existing…

Large scale Natural Language Understanding (NLU) systems are typically trained on large quantities of data, requiring a fast and scalable training strategy. A typical design for NLU systems consists of domain-level NLU modules (domain…

This paper reexamines the research on out-of-distribution (OOD) robustness in the field of NLP. We find that the distribution shift settings in previous studies commonly lack adequate challenges, hindering the accurate evaluation of OOD…

Recent alignment techniques, such as reinforcement learning from human feedback, have been widely adopted to align large language models with human preferences by learning and leveraging reward models. In practice, these models often…

Large language models are increasingly deployed across diverse applications. This often includes tasks LLMs have not encountered during training. This implies that enumerating and obtaining the high-quality training data for all tasks is…

In recent years, we have witnessed a dramatic shift towards techniques driven by neural networks for a variety of NLP tasks. Undoubtedly, neural language models (NLMs) have reduced perplexity by impressive amounts. This progress, however,…

Deep neural networks have achieved remarkable results across many language processing tasks, however these methods are highly sensitive to noise and adversarial attacks. We present a regularization based method for limiting network…

Neural machine translation benefits from semantically rich representations. Considerable progress in learning such representations has been achieved by language modelling and mutual information maximization objectives using contrastive…

Knowing the reliability of a model's response is essential in practical applications. Given the strong generation capabilities of large language models (LLMs), research has focused on generating verbalized confidence. This approach is…

Simplicity bias poses a significant challenge in neural networks, often leading models to favor simpler solutions and inadvertently learn decision rules influenced by spurious correlations. This results in biased models with diminished…

Many industrial machine learning (ML) systems require frequent retraining to keep up-to-date with constantly changing data. This retraining exacerbates a large challenge facing ML systems today: model training is unstable, i.e., small…