Related papers: Vector Graph-Based Repository Understanding for Is…

Recent advancements in Large Language Models (LLMs) have transformed code generation from natural language queries. However, despite their extensive knowledge and ability to produce high-quality code, LLMs often struggle with contextual…

Software repositories contain valuable information for understanding the development process. However, extracting insights from repository data is time-consuming and requires technical expertise. While software engineering chatbots support…

Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis. Conventional retrieval methods based on keyword search or static embeddings often fail to answer…

Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic…

Thanks to recent advancements in machine learning, vector-based methods have been adopted in many modern information retrieval (IR) systems. While showing promising retrieval performance, these approaches typically fail to explain why a…

The continuous evolution of system specifications necessitates frequent evaluation of conflicting requirements, a process that is traditionally labour intensive. Although large language models (LLMs) have demonstrated significant potential…

We propose a scalable and cost-efficient framework for deploying Graph-based Retrieval-Augmented Generation (GraphRAG) in enterprise environments. While GraphRAG has shown promise for multi- hop reasoning and structured retrieval, its…

Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a repository scale.…

Industrial standards and normative documents exhibit intricate hierarchical structures, domain-specific lexicons, and extensive cross-referential dependencies, which making it challenging to process them directly by Large Language Models…

We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our…

Large Language Models (LLMs) increasingly rely on knowledge graphs for factual reasoning, yet how retrieval design shapes their performance remains unclear. We examine how question decomposition changes the retrieved subgraph's content and…

Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of…

Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts. Two tropes of architectures have emerged -- transformer-based models inspired by LLMs,…

Word embeddings are rich word representations, which in combination with deep neural networks, lead to large performance gains for many NLP tasks. However, word embeddings are represented by dense, real-valued vectors and they are therefore…

Large language models (LLMs) exhibit strong semantic understanding, yet struggle when user instructions involve ambiguous or conceptually misaligned terms. We propose the Language Graph Model (LGM) to enhance conceptual clarity by…

Vector databases typically rely on approximate nearest neighbor (ANN) search to retrieve the top-k closest vectors to a query in embedding space. While effective, this approach often yields semantically redundant results, missing the…

Selecting the right knowledge is critical when using large language models (LLMs) to solve domain-specific data analysis tasks. However, most retrieval-augmented approaches rely primarily on lexical or embedding similarity, which is often a…

We consider the problem of developing suitable learning representations (embeddings) for library packages that capture semantic similarity among libraries. Such representations are known to improve the performance of downstream learning…

Repository-level coding agents must first localize the files and symbols relevant to a task; failures at this stage can cascade across downstream objectives ranging from patch generation to test writing and codebase question answering.…

Polymer literature contains a large and growing body of experimental knowledge, yet much of it is buried in unstructured text and inconsistent terminology, making systematic retrieval and reasoning difficult. Existing tools typically…