Related papers: Multi-span Style Extraction for Generative Reading…

Multi-choice Machine Reading Comprehension (MRC) as a challenge requires models to select the most appropriate answer from a set of candidates with a given passage and question. Most of the existing researches focus on the modeling of…

We propose a novel method for applying Transformer models to extractive question answering (QA) tasks. Recently, pretrained generative sequence-to-sequence (seq2seq) models have achieved great success in question answering. Contributing to…

Despite the significant progress of large language models (LLMs) in various tasks, they often produce factual errors due to their limited internal knowledge. Retrieval-Augmented Generation (RAG), which enhances LLMs with external knowledge…

Relation extraction (RE) is an important information extraction task which provides essential information to many NLP applications such as knowledge base population and question answering. In this paper, we present a novel generative model…

Retrieval-Augmented Generation (RAG) systems commonly use chunking strategies for retrieval, which enhance large language models (LLMs) by enabling them to access external knowledge, ensuring that the retrieved information is up-to-date and…

Column generation (CG) is one of the most successful approaches for solving large-scale linear programming (LP) problems. Given an LP with a prohibitively large number of variables (i.e., columns), the idea of CG is to explicitly consider…

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Large Reasoning Models (LRMs) have shown remarkable performance on challenging questions, such as math and coding. However, to obtain a high quality solution, one may need to sample more than once. In principal, there are two sampling…

In question answering requiring common sense, language models (e.g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work,…

The paper presents a data-driven approach to information extraction (viewed as template filling) using the structured language model (SLM) as a statistical parser. The task of template filling is cast as constrained parsing using the SLM.…

Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models. Besides, existing approaches are also…

Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retrieval remains…

This paper introduces a new information extraction model for business documents. Different from prior studies which only base on span extraction or sequence labeling, the model takes into account advantage of both span extraction and…

A Retrieval-Augmented Generation (RAG) model powered by a large language model (LLM) provides a faster and more cost-effective solution for adapting to new data and knowledge. It also delivers more specialized responses compared to…

Generative information retrieval, encompassing two major tasks of Generative Document Retrieval (GDR) and Grounded Answer Generation (GAR), has gained significant attention in the area of information retrieval and natural language…

Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so by sharpening the distribution over full generated outputs, favoring completions that are…

Since their introduction, diffusion models have quickly become the prevailing approach to generative modeling in many domains. They can be interpreted as learning the gradients of a time-varying sequence of log-probability density…

Multimodal large language models (MLLMs) have recently shown great progress in text-rich image understanding, yet they still struggle with complex, multi-page visually-rich documents. Traditional methods using document parsers for…

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…

In this thesis we examined several multimodal feature extraction and learning methods for retrieval and classification purposes. We reread briefly some theoretical results of learning in Section 2 and reviewed several generative and…