Related papers: ProUIE: A Macro-to-Micro Progressive Learning Meth…

We introduce AI University (AI-U), a flexible framework for AI-driven course content delivery that adapts to instructors' teaching styles. At its core, AI-U fine-tunes a large language model (LLM) with retrieval-augmented generation (RAG)…

An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but…

Real-time low-light image enhancement on mobile and embedded devices requires models that balance visual quality and computational efficiency. Existing deep learning methods often rely on large networks and labeled datasets, limiting their…

Large Language Models (LLMs) can be seen as compressed knowledge bases, but it remains unclear what knowledge they truly contain and how far their knowledge boundary extends. Existing benchmarks are mostly static and provide limited support…

Open Information Extraction (OIE) systems seek to compress the factual propositions of a sentence into a series of n-ary tuples. These tuples are useful for downstream tasks in natural language processing like knowledge base creation,…

Document-level information extraction (IE) is a crucial task in natural language processing (NLP). This paper conducts a systematic review of recent document-level IE literature. In addition, we conduct a thorough error analysis with…

While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new data is…

Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing methods (like ACE or GEPA) can learn system prompts to…

Web information extraction (WIE) is an important part of many e-commerce systems, supporting tasks like customer analysis and product recommendation. In this work, we look at the problem of building up-to-date product databases by…

Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE models have focused primarily on coarse-grained MoE…

The evolving sophistication and intricacies of Large Language Models (LLMs) yield unprecedented advancements, yet they simultaneously demand considerable computational resources and incur significant costs. To alleviate these challenges,…

Text structuralization is one of the important fields of natural language processing (NLP) consists of information extraction (IE) and structure formalization. However, current studies of text structuralization suffer from a shortage of…

Dense vector retrieval is the practical backbone of Retrieval- Augmented Generation (RAG), but similarity search can suffer from precision limitations. Conversely, utility-based approaches leveraging LLM re-ranking often achieve superior…

Large Language Models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove…

The integration of large language models (LLMs) and search engines represents a significant evolution in knowledge acquisition methodologies. However, determining the knowledge that an LLM already possesses and the knowledge that requires…

\textbf{Objective:} We aimed to develop an advanced multi-task large language model (LLM) framework to extract multiple types of information about dietary supplements (DS) from clinical records. \textbf{Methods:} We used four core DS…

Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual…

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…

In industrial machine learning pipelines, data often arrive in parts. Particularly in the case of deep neural networks, it may be too expensive to train the model from scratch each time, so one would rather use a previously learned model…