Related papers: BoundRL: Efficient Structured Text Segmentation th…
Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and…
Recent advancements in open vocabulary models, like CLIP, have notably advanced zero-shot classification and segmentation by utilizing natural language for class-specific embeddings. However, most research has focused on improving model…
Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting…
Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. However, existing methods predominantly rely on response-level…
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…
Large language models excel at complex tasks by breaking down problems into structured reasoning steps. However, reasoning traces often extend beyond reaching a correct answer, causing wasted computation, reduced readability, and…
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…
Large language models (LLMs), including zero-shot and few-shot paradigms, have shown promising capabilities in clinical text generation. However, real-world applications face two key challenges: (1) patient data is highly unstructured,…
Due to the rapid development of large language models, people increasingly often encounter texts that may start as written by a human but continue as machine-generated. Detecting the boundary between human-written and machine-generated…
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…
Recent years have witnessed increasing interests in prompt-based learning in which models can be trained on only a few annotated instances, making them suitable in low-resource settings. When using prompt-based learning for text…
Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…
Semi-supervised semantic segmentation has attracted increasing attention in computer vision, aiming to leverage unlabeled data through latent supervision. To achieve this goal, prototype-based classification has been introduced and achieved…
Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge and perception. Retrieval-augmented generation (RAG) addresses this by retrieving…
Managing extensive context remains a critical bottleneck for Large Language Models (LLMs), particularly in applications like long-document question answering and autonomous agents where lengthy inputs incur high computational costs and…
Efficiently processing and interpreting network data is critical for the operation of increasingly complex networks. Recent advances in Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) techniques have improved data…
Prompt compression methods enhance the efficiency of Large Language Models (LLMs) and minimize the cost by reducing the length of input context. The goal of prompt compression is to shorten the LLM prompt while maintaining a high generation…
Retrieval-augmented generation (RAG) has become a transformative approach for enhancing large language models (LLMs) by grounding their outputs in external knowledge sources. Yet, a critical question persists: how can vast volumes of…
Applying Reinforcement Learning (RL) to sequence generation models enables the direct optimization of long-term rewards (\textit{e.g.,} BLEU and human feedback), but typically requires large-scale sampling over a space of action sequences.…
Entity search, i.e., finding the most similar entities to a query entity, faces unique challenges in e-commerce, where product similarity varies across categories and contexts. Traditional embedding-based approaches often struggle to…