Related papers: How Does Beam Search improve Span-Level Confidence…

This paper attempts multi-label classification by extending the idea of independent binary classification models for each output label, and exploring how the inherent correlation between output labels can be used to improve predictions.…

Using prompts to explore the knowledge contained within pre-trained language models for downstream tasks has now become an active topic. Current prompt tuning methods mostly convert the downstream tasks to masked language modeling problems…

Multi-label text classification involves extracting all relevant labels from a sentence. Given the unordered nature of these labels, we propose approaching the problem as a set prediction task. To address the correlation between labels, we…

Probing has become an important tool for analyzing representations in Natural Language Processing (NLP). For graphical NLP tasks such as dependency parsing, linear probes are currently limited to extracting undirected or unlabeled parse…

In computer vision pixelwise dense prediction is the task of predicting a label for each pixel in the image. Convolutional neural networks achieve good performance on this task, while being computationally efficient. In this paper we carry…

Diffusion models have recently driven significant breakthroughs in generative modeling. While state-of-the-art models produce high-quality samples on average, individual samples can still be low quality. Detecting such samples without human…

Emotion recognition (ER) is an important task in Natural Language Processing (NLP), due to its high impact in real-world applications from health and well-being to author profiling, consumer analysis and security. Current approaches to ER,…

In multi-label classification, where a single example may be associated with several class labels at the same time, the ability to model dependencies between labels is considered crucial to effectively optimize non-decomposable evaluation…

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in…

The advent of large language models (LLMs) has dramatically advanced the state-of-the-art in numerous natural language generation tasks. For LLMs to be applied reliably, it is essential to have an accurate measure of their confidence.…

Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The…

Structured prediction energy networks (SPENs; Belanger & McCallum 2016) use neural network architectures to define energy functions that can capture arbitrary dependencies among parts of structured outputs. Prior work used gradient descent…

Current advances in Natural Language Processing (NLP) have made it increasingly feasible to build applications leveraging textual data. Generally, the core of these applications rely on having a good semantic representation of text into…

The accuracy of deep neural networks is significantly influenced by the effectiveness of mini-batch construction during training. In single-label scenarios, such as binary and multi-class classification tasks, it has been demonstrated that…

In Retrieval-Augmented Generation (RAG) tasks using Large Language Models (LLMs), the quality of retrieved information is critical to the final output. This paper introduces the IRSC benchmark for evaluating the performance of embedding…

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…

We derive a novel generative model from iterative Gaussian posterior inference. By treating the generated sample as an unknown variable, we can formulate the sampling process in the language of Bayesian probability. Our model uses a…

Sequential dependencies present a fundamental bottleneck in deploying large-scale autoregressive models, particularly for real-time applications. While traditional optimization approaches like pruning and quantization often compromise model…

Assessing the reliability of Large Language Models (LLMs) by confidence elicitation is a prominent approach to AI safety in high-stakes applications, such as healthcare and finance. Existing methods either require expensive computational…

Plug-and-play functionality allows deep learning models to adapt well to different tasks without requiring any parameters modified. Recently, prefix-tuning was shown to be a plug-and-play method on various text generation tasks by simply…