Related papers: SIMPL: A DSL for Automatic Specialization of Infer…
Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality…
In-context learning (ICL) allows transformer-based language models that are pre-trained on general text to quickly learn a specific task with a few "task demonstrations" without updating their parameters, significantly boosting their…
Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…
Probabilistic programming has emerged as a powerful paradigm in statistics, applied science, and machine learning: by decoupling modelling from inference, it promises to allow modellers to directly reason about the processes generating…
Sentiment Analysis (SA) is a crucial aspect of Natural Language Processing (NLP), focusing on identifying and interpreting subjective assessments in textual content. Syntactic parsing is useful in SA as it improves accuracy and provides…
In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitable prompts from a…
Language models (LMs) excel at tasks across diverse domains, yet require substantial computational resources during inference. Compression techniques such as pruning and quantization offer a practical path towards efficient LM deployment,…
This paper looks at semi-supervised learning (SSL) for image-based text recognition. One of the most popular SSL approaches is pseudo-labeling (PL). PL approaches assign labels to unlabeled data before re-training the model with a…
Metadata attributes (e.g., user and product IDs from reviews) can be incorporated as additional inputs to neural-based NLP models, by modifying the architecture of the models, in order to improve their performance. Recent models however…
Scaling inference compute in large language models (LLMs) through repeated sampling consistently increases the coverage (fraction of problems solved) as the number of samples increases. We conjecture that this observed improvement is…
Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in large language models (LLMs) have enabled in-context learning (ICL), allowing LLMs to acquire proficiency…
Although significant progress achieved, multi-label classification is still challenging due to the complexity of correlations among different labels. Furthermore, modeling the relationships between input and some (dull) classes further…
Fine-grained image classification has witnessed significant advancements with the advent of deep learning and computer vision technologies. However, the scarcity of detailed annotations remains a major challenge, especially in scenarios…
Self-supervised learning (SSL) has developed rapidly in recent years. However, most of the mainstream methods are computationally expensive and rely on two (or more) augmentations for each image to construct positive pairs. Moreover, they…
This paper presents a novel approach named \textbf{C}ontextually \textbf{R}elevant \textbf{I}mputation leveraging pre-trained \textbf{L}anguage \textbf{M}odels (\textbf{CRILM}) for handling missing data in tabular datasets. Instead of…
Overview of inference methods in PLoM.
Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often require multi-step reasoning over the retrieved information, with no clear or…
Continuous pseudo-labeling (PL) algorithms such as slimIPL have recently emerged as a powerful strategy for semi-supervised learning in speech recognition. In contrast with earlier strategies that alternated between training a model and…
Performing inference on large volumes of samples with large language models (LLMs) can be computationally and financially costly in industry and real-world use. We propose batch prompting, a simple yet effective prompting approach that…
A common classification task situation is where one has a large amount of data available for training, but only a small portion is annotated with class labels. The goal of semi-supervised training, in this context, is to improve…