Related papers: Beyond Chunk-Then-Embed: A Comprehensive Taxonomy …
Retrieval-Augmented Generation (RAG) systems using large language models (LLMs) often generate inaccurate responses due to the retrieval of irrelevant or loosely related information. Existing methods, which operate at the document level,…
Code completion can help developers improve efficiency and ease the development lifecycle. Although code completion is available in modern integrated development environments (IDEs), research lacks in determining what makes a good context…
Text embeddings from Large Language Models (LLMs) have become foundational for numerous applications. However, these models typically operate on raw text, overlooking the rich structural information, such as hyperlinks or citations, that…
Existing long-document question answering systems typically process texts as flat sequences or use heuristic chunking, which overlook the discourse structures that naturally guide human comprehension. We present a discourse-aware…
Retrieval-Augmented Generation (RAG) has emerged as a framework to address the constraints of Large Language Models (LLMs). Yet, its effectiveness fundamentally hinges on document chunking - an often-overlooked determinant of its quality.…
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…
Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when analyzing long documents. When long documents are processed sequentially, early or dominant…
Document chunking is a crucial component of Retrieval-Augmented Generation (RAG), as it directly affects the retrieval of relevant and precise context. Conventional fixed-length and recursive splitters often produce arbitrary, incoherent…
Multi-vector models dominate Visual Document Retrieval (VDR) due to their fine-grained matching capabilities, but their high storage and computational costs present a major barrier to practical deployment. In this paper, we propose…
Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail…
Large Language Models (LLMs) continue to advance natural language processing with their ability to generate human-like text across a range of tasks. Despite the remarkable success of LLMs in Natural Language Processing (NLP), their…
Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation…
Retrieval-Augmented Generation (RAG) enhances the response capabilities of language models by integrating external knowledge sources. However, document chunking as an important part of RAG system often lacks effective evaluation tools. This…
We study how document chunking choices impact the reliability of Retrieval-Augmented Generation (RAG) systems in industry. While practice often relies on heuristics, our end-to-end evaluation on Natural Questions systematically varies…
With the development of pre-trained language models, the dense retrieval models have become promising alternatives to the traditional retrieval models that rely on exact match and sparse bag-of-words representations. Different from most…
Dense document embeddings are central to neural retrieval. The dominant paradigm is to train and construct embeddings by running encoders directly on individual documents. In this work, we argue that these embeddings, while effective, are…
Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by randomly concatenating documents of various lengths and then chunking them into sequences of a…
Chunking information is a key step in Retrieval Augmented Generation (RAG). Current research primarily centers on paragraph-level chunking. This approach treats all texts as equal and neglects the information contained in the structure of…
Breaking long documents into smaller segments is a fundamental challenge in information retrieval. Whether for search engines, question-answering systems, or retrieval-augmented generation (RAG), effective segmentation determines how well…
Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a…