相关论文: Take It Easy: Label-Adaptive Self-Rationalization …

Accurate lane detection, a crucial enabler for autonomous driving, currently relies on obtaining a large and diverse labeled training dataset. In this work, we explore learning from abundant, randomly generated synthetic data, together with…

Unsupervised pre-training has led to much recent progress in natural language understanding. In this paper, we study self-training as another way to leverage unlabeled data through semi-supervised learning. To obtain additional data for a…

Attention mechanism is contributing to the majority of recent advances in machine learning for natural language processing. Additionally, it results in an attention map that shows the proportional influence of each input in its decision.…

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…

Capturing the interesting components of an image is a key aspect of image understanding. When a speaker annotates an image, selecting labels that are informative greatly depends on the prior knowledge of a prospective listener. Motivated by…

Most existing work on automated fact checking is concerned with predicting the veracity of claims based on metadata, social network spread, language used in claims, and, more recently, evidence supporting or denying claims. A crucial piece…

Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning…

Large language models have the potential to generate explanations for their own predictions in a variety of styles based on user instructions. Recent research has examined whether these self-explanations faithfully reflect the models'…

Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment. Existing calibration methods usually depend on labels or repeated sampling at…

Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain…

Not all tags are relevant to an image, and the number of relevant tags is image-dependent. Although many methods have been proposed for image auto-annotation, the question of how to determine the number of tags to be selected per image…

When constructing models that learn from noisy labels produced by multiple annotators, it is important to accurately estimate the reliability of annotators. Annotators may provide labels of inconsistent quality due to their varying…

Natural Language Inference (NLI) remains an important benchmark task for LLMs. NLI datasets are a springboard for transfer learning to other semantic tasks, and NLI models are standard tools for identifying the faithfulness of…

Large crowdsourced datasets are widely used for training and evaluating neural models on natural language inference (NLI). Despite these efforts, neural models have a hard time capturing logical inferences, including those licensed by…

Verifying mathematical proofs is difficult, but can be automated with the assistance of a computer. Autoformalization is the task of automatically translating natural language mathematics into a formal language that can be verified by a…

Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the…

Grounded text generation systems often generate text that contains factual inconsistencies, hindering their real-world applicability. Automatic factual consistency evaluation may help alleviate this limitation by accelerating evaluation…

Training a model to provide natural language explanations (NLEs) for its predictions usually requires the acquisition of task-specific NLEs, which is time- and resource-consuming. A potential solution is the few-shot out-of-domain transfer…

A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a…

Test-time adaptation (TTA) aims to adapt a trained classifier using online unlabeled test data only, without any information related to the training procedure. Most existing TTA methods adapt the trained classifier using the classifier's…