Related papers: LumberChunker: Long-Form Narrative Document Segmen…

Log parsing serves as an essential prerequisite for various log analysis tasks. Recent advancements in this field have improved parsing accuracy by leveraging the semantics in logs through fine-tuning large language models (LLMs) or…

While numerous architectures for long-range language models (LRLMs) have recently been proposed, a meaningful evaluation of their discourse-level language understanding capabilities has not yet followed. To this end, we introduce…

Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previous research typically handles paragraphs from external…

Large language models (LLMs) have exhibited remarkable few-shot learning capabilities and unified the paradigm of NLP tasks through the in-context learning (ICL) technique. Despite the success of ICL, the quality of the exemplar…

This paper presents a novel method for parsing and vectorizing semi-structured data to enhance the functionality of Retrieval-Augmented Generation (RAG) within Large Language Models (LLMs). We developed a comprehensive pipeline for…

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…

Long text classification is challenging for Large Language Models (LLMs) due to token limits and high computational costs. This study explores whether a Retrieval Augmented Generation (RAG) approach using only the most relevant text…

Document retrieval is one of the most challenging tasks in Information Retrieval. It requires handling longer contexts, often resulting in higher query latency and increased computational overhead. Recently, Learned Sparse Retrieval (LSR)…

Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents, sequential reading of large portions of text…

Large Language Models (LLMs) have emerged as powerful tools for passage reranking in information retrieval, leveraging their superior reasoning capabilities to address the limitations of conventional models on complex queries. However,…

Recent multimodal large language models (MLLMs) still struggle with long document understanding due to two fundamental challenges: information interference from abundant irrelevant content, and the quadratic computational cost of…

Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers.…

Long document re-ranking has been a challenging problem for neural re-rankers based on deep language models like BERT. Early work breaks the documents into short passage-like chunks. These chunks are independently mapped to scalar scores or…

The rise of large language models (LLMs) has created an urgent need to distinguish between human-written and LLM-generated text to ensure authenticity and societal trust. Existing detectors typically provide a binary classification for an…

Screening patients for enrollment is a well-known, labor-intensive bottleneck that leads to under-enrollment and, ultimately, trial failures. Recent breakthroughs in large language models (LLMs) offer a promising opportunity to use…

Large Language Model agents often retrieve context from knowledge bases that lack structural consistency with the agent's current reasoning state, leading to incoherent reasoning chains. We introduce Path-Constrained Retrieval (PCR), a…

In this study, we compare the performance of four text chunking approaches: Recursive, Khmer-Aware, Sentence-Based, and LLM-Based within a Retrieval-Augmented Generation (RAG) framework applied to Khmer agricultural documents. The document…

Financial news plays a crucial role in decision-making processes across the financial sector, yet the efficient processing of this information into a structured format remains challenging. This paper presents a novel approach to financial…

Large language models (LLMs) have demonstrated strong performance in sentence-level machine translation, but scaling to document-level translation remains challenging, particularly in modeling long-range dependencies and discourse phenomena…

Deforestation is a compiler optimization that removes intermediate data structure allocations from functional programs to improve their efficiency. This is an old idea, but previous approaches have proved limited or impractical: they either…