Related papers: Joint Information Extraction Across Classical and …
Parameter-efficient tuning (PEFT) techniques like low-rank adaptation (LoRA) offer training efficiency on Large Language Models, but their impact on model performance remains limited. Recent efforts integrate LoRA and Mixture-of-Experts…
Mixture of Experts (MoE) architectures have recently advanced the scalability and adaptability of large language models (LLMs) for continual multimodal learning. However, efficiently extending these models to accommodate sequential tasks…
Large language models (LLMs) usually fall short on information extraction (IE) tasks and struggle to follow the complex instructions of IE tasks. This primarily arises from LLMs not being aligned with humans, as mainstream alignment…
In-context reinforcement learning (ICRL) has emerged as a promising paradigm for adapting RL agents to downstream tasks through prompt conditioning. However, two notable challenges remain in fully harnessing in-context learning within RL…
Multi-domain recommendation and multi-task recommendation have demonstrated their effectiveness in leveraging common information from different domains and objectives for comprehensive user modeling. Nonetheless, the practical…
In the rapidly evolving field of healthcare, the integration of artificial intelligence (AI) has become a pivotal component in the automation of clinical workflows, ushering in a new era of efficiency and accuracy. This study focuses on the…
Joint entity-relation extraction is a critical task in transforming unstructured or semi-structured text into triplets, facilitating the construction of large-scale knowledge graphs, and supporting various downstream applications. Despite…
The multi-format information extraction task in the 2021 Language and Intelligence Challenge is designed to comprehensively evaluate information extraction from different dimensions. It consists of an multiple slots relation extraction…
Since real-world ubiquitous documents (e.g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic. Most existing works decouple the problem into two separate tasks,…
Standard LoRA fine-tuning of Mixture-of-Experts (MoE) models applies adapters to every expert, yet our profiling shows that per-layer expert routing is highly skewed: a small subset of experts handles most tokens in each layer, while many…
Low-Rank Adaptation (LoRA) provides an effective yet efficient solution for fine-tuning large language models (LLM). The modular and plug-and-play nature of LoRA enables the integration of diverse domain-specific LoRAs to enhance the…
Information Extraction (IE) from the tables present in scientific articles is challenging due to complicated tabular representations and complex embedded text. This paper presents TabLeX, a large-scale benchmark dataset comprising table…
Multilingual Information Retrieval is increasingly important in real-world search settings, where users issue queries over mixed-language corpora. Existing evaluations mainly reward language-agnostic semantic relevance, treating relevant…
Large Language Models (LLMs) demonstrate exceptional performance in textual understanding and tabular reasoning tasks. However, their ability to comprehend and analyze hybrid text, containing textual and tabular data, remains unexplored.…
Mixture-of-Experts (MoE) architectures have shown strong multilingual capabilities, yet the internal mechanisms underlying performance gains and cross-language differences remain insufficiently understood. In this work, we conduct a…
In a highly multilingual and multicultural environment such as in the European Commission with soon over twenty official languages, there is an urgent need for text analysis tools that use minimal linguistic knowledge so that they can be…
In 5G smart cities, edge computing is employed to provide nearby computing services for end devices, and the large-scale models (e.g., GPT and LLaMA) can be deployed at the network edge to boost the service quality. However, due to the…
Knowledge of the medical decision process, which can be modeled as medical decision trees (MDTs), is critical to building clinical decision support systems. However, current MDT construction methods rely heavily on time-consuming and…
Open Information Extraction (OpenIE) extracts meaningful structured tuples from free-form text. Most previous work on OpenIE considers extracting data from one sentence at a time. We describe NeurON, a system for extracting tuples from…
Information extraction (IE) from unstructured documents remains a critical challenge in data processing pipelines. Traditional optical character recognition (OCR) methods and conventional parsing engines demonstrate limited effectiveness…