Related papers: An AI-Resilient Text Rendering Technique for Readi…
LLM-based prompt optimization, that uses LLM-provided "textual gradients" (feedback) to refine prompts, has emerged an effective method for automatic prompt engineering. However, its scalability and stability are unclear when using more…
Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do…
Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a range of downstream tasks. While optimizing the context can be effective for improving performance on specific tasks, it can often…
Text segmentation is important for signaling a document's structure. Without segmenting a long document into topically coherent sections, it is difficult for readers to comprehend the text, let alone find important information. The problem…
Text Classification is the most essential and fundamental problem in Natural Language Processing. While numerous recent text classification models applied the sequential deep learning technique, graph neural network-based models can…
Existing techniques for text detection can be broadly classified into two primary groups: segmentation-based and regression-based methods. Segmentation models offer enhanced robustness to font variations but require intricate…
In text classification tasks, fine tuning pretrained language models like BERT and GPT-3 yields competitive accuracy; however, both methods require pretraining on large text datasets. In contrast, general topic modeling methods possess the…
Pretrained generative models have opened new frontiers in brain decoding by enabling the synthesis of realistic texts and images from non-invasive brain recordings. However, the reliability of such outputs remains questionable--whether they…
Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the…
Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task is that rare, polysemous, and ambiguous words frequently appear in images, e.g., names of places, products, and…
Optimization, a key tool in machine learning and statistics, relies on regularization to reduce overfitting. Traditional regularization methods control a norm of the solution to ensure its smoothness. Recently, topological methods have…
We propose a method to learn unsupervised sentence representations in a non-compositional manner based on Generative Latent Optimization. Our approach does not impose any assumptions on how words are to be combined into a sentence…
Retrieval augmentation has become an effective solution to empower large language models (LLMs) with external and verified knowledge sources from the database, which overcomes the limitations and hallucinations of LLMs in handling…
One of the significant challenges of deep neural networks is that the complex nature of the network prevents human comprehension of the outcome of the network. Consequently, the applicability of complex machine learning models is limited in…
Text summarization systems have made significant progress in recent years, but typically generate summaries in one single step. However, the one-shot summarization setting is sometimes inadequate, as the generated summary may contain…
We introduce a novel scheme for parsing a piece of text into its Abstract Meaning Representation (AMR): Graph Spanning based Parsing (GSP). One novel characteristic of GSP is that it constructs a parse graph incrementally in a top-down…
Most recent neural semi-supervised learning algorithms rely on adding small perturbation to either the input vectors or their representations. These methods have been successful on computer vision tasks as the images form a continuous…
Recurrent neural networks (RNNs), such as long short-term memory networks (LSTMs), serve as a fundamental building block for many sequence learning tasks, including machine translation, language modeling, and question answering. In this…
This paper describes an investigation of the robustness of large language models (LLMs) for retrieval augmented generation (RAG)-based summarization tasks. While LLMs provide summarization capabilities, their performance in complex,…
Transformers have a quadratic scaling of computational complexity with input size, which limits the input context window size of large language models (LLMs) in both training and inference. Meanwhile, retrieval-augmented generation (RAG)…