Related papers: IE as Cache: Information Extraction Enhanced Agent…

Recent advances in agentic systems for data analysis have emphasized automation of insight generation through multi-agent frameworks, and orchestration layers. While these systems effectively manage tasks like query translation, data…

Current research on the advantages and trade-offs of using characters, instead of tokenized text, as input for deep learning models, has evolved substantially. New token-free models remove the traditional tokenization step; however, their…

We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment…

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful…

Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations, existing approaches preserve either the agent's trajectory, passive access to…

The theoretical foundations of a new model and paradigm (called TIE) for data storage and access are introduced. Associations between data elements are stored in a single Matrix table, which is usually kept entirely in RAM for quick access.…

Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by incorporating external knowledge bases, but this may expose them to extraction attacks, leading to potential copyright and privacy risks. However, existing…

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…

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful…

The static nature of knowledge within Large Language Models (LLMs) makes it difficult for them to adapt to evolving information, rendering knowledge editing a critical task. However, existing methods struggle with challenges of scalability…

Concept learning is a form of supervised machine learning that operates on knowledge bases in description logics. State-of-the-art concept learners often rely on an iterative search through a countably infinite concept space. In each…

Prior works formulate the extraction of event-specific arguments as a span extraction problem, where event arguments are explicit -- i.e. assumed to be contiguous spans of text in a document. In this study, we revisit this definition of…

Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental…

A real-world information extraction (IE) system for semi-structured document images often involves a long pipeline of multiple modules, whose complexity dramatically increases its development and maintenance cost. One can instead consider…

With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing…

Information extraction (IE) is an important task in Natural Language Processing (NLP), involving the extraction of named entities and their relationships from unstructured text. In this paper, we propose a novel approach to this task by…

Retrieval-augmented generation (RAG) improves factual grounding, yet most systems rely on flat chunk retrieval and provide limited control over multi-step synthesis. We propose an Explainable Innovation Engine that upgrades the knowledge…

Retrieval-augmented generation (RAG) systems address complex user requests by decomposing them into subqueries, retrieving potentially relevant documents for each, and then aggregating them to generate an answer. Efficiently selecting…

While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks and apply them in future contexts. To address this limitation, we…

We propose the Intuitive Reasoning Network (IRENE) - a novel neural model for intuitive psychological reasoning about agents' goals, preferences, and actions that can generalise previous experiences to new situations. IRENE combines a graph…