Related papers: Instruction Embedding: Latent Representations of I…
Large language models (LLMs) have increasingly been explored as powerful text embedders. Existing LLM-based text embedding approaches often leverage the embedding of the final token, typically a reserved special token such as [EOS].…
As research in large language models (LLMs) continues to accelerate, LLM-based evaluation has emerged as a scalable and cost-effective alternative to human evaluations for comparing the ever increasing list of models. This paper…
Visual instruction tuning is the key to building large vision language models~(LVLMs), which can greatly improve the task generalization and solving capabilities by learning a mixture of instruction data from diverse visual tasks. Previous…
Word embeddings are the interface between the world of discrete units of text processing and the continuous, differentiable world of neural networks. In this work, we examine various random and pretrained initialization methods for…
Multimodal Large Language Models advance multimodal representation learning by acquiring transferable semantic embeddings, thereby substantially enhancing performance across a range of vision-language tasks, including cross-modal retrieval,…
The recently occurred representation learning make an attractive performance in NLP and complex network, it is becoming a fundamental technology in machine learning and data mining. How to use representation learning to improve the…
Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful methodological approaches and sufficiently large datasets prevents…
Recent studies on knowledge graph embedding focus on mapping entities and relations into low-dimensional vector spaces. While most existing models primarily exploit structural information, knowledge graphs also contain rich contextual and…
Large language models (LLMs) are rapidly transforming knowledge work by improving the quality and efficiency of tasks such as writing, coding, and data analysis. However, their growing use in education has exposed a learning-performance…
We consider the large-scale query-document retrieval problem: given a query (e.g., a question), return the set of relevant documents (e.g., paragraphs containing the answer) from a large document corpus. This problem is often solved in two…
Most language models (LMs) are trained and applied in an autoregressive left-to-right fashion, assuming that the next token only depends on the preceding ones. However, this assumption ignores the potential benefits of using the full…
Lately, instruction-based techniques have made significant strides in improving performance in few-shot learning scenarios. They achieve this by bridging the gap between pre-trained language models and fine-tuning for specific downstream…
While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves. To that end, we introduce dynamic…
For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
The embedding-based representation learning is commonly used in deep learning recommendation models to map the raw sparse features to dense vectors. The traditional embedding manner that assigns a uniform size to all features has two…
Recent work exploring the capabilities of pre-trained large language models (LLMs) has demonstrated their ability to act as general pattern machines by completing complex token sequences representing a wide array of tasks, including…
The interaction with Large Language Models (LLMs) through instructions has been extensively investigated in the research community. While instructions have been widely used as the guidelines for task solving, this paper further notices that…
Interpretable entity representations (IERs) are sparse embeddings that are "human-readable" in that dimensions correspond to fine-grained entity types and values are predicted probabilities that a given entity is of the corresponding type.…
Recommender systems have seen significant advancements with the influence of deep learning and graph neural networks, particularly in capturing complex user-item relationships. However, these graph-based recommenders heavily depend on…