Related papers: On the Dynamical Generation of Quark-Level-Linear-…

Recent literature highlights the potential of graph-based approaches within large language model (LLM) retrieval-augmented generation (RAG) pipelines for answering queries of varying complexity, particularly those that fall outside the…

Graph Retrieval-Augmented Generation (GraphRAG) has proven highly effective in enhancing the performance of Large Language Models (LLMs) on tasks that require external knowledge. By leveraging Knowledge Graphs (KGs), GraphRAG improves…

In this paper, we propose the task of consecutive question generation (CQG), which generates a set of logically related question-answer pairs to understand a whole passage, with a comprehensive consideration of the aspects including…

We propose a supersymmetric composite model with three generations in which supersymmetry and electroweak symmetry are broken dynamically, and masses of quarks and leptons are generated without introducing any mass scales by hand. All the…

Semantic Knowledge Graphs (SKG) face challenges with scalability, flexibility, contextual understanding, and handling unstructured or ambiguous information. However, they offer formal and structured knowledge enabling highly interpretable…

A large amount of observational data has been accumulated in various fields in recent times, and there is a growing need to estimate the generating processes of these data. A linear non-Gaussian acyclic model (LiNGAM) based on the…

Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models (LLMs). Targeting its bottleneck of retriever performance, "generate-then-read" pipeline is proposed to replace the…

Lifelong sequence generation (LSG), a problem in continual learning, aims to continually train a model on a sequence of generation tasks to learn constantly emerging new generation patterns while avoiding the forgetting of previous…

One type of dynamical generation consists in the formation of multiple hadronic resonances from single seed states by incorporating hadronic loop contributions on the level of $s$-wave propagators. Along this line, we study the propagator…

We systematically study the phases of generic toric singularities, using methods initiated in hep-th/0612046. These correspond to Gauged Linear Sigma Models with arbitrary charges. We show that complete information about generic $U(1)^r$…

Dynamical systems theory provides a framework for analyzing iterative processes and evolution over time. Within such systems, repetitive transformations can lead to stable configurations, known as attractors, including fixed points and…

Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and…

Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks but struggles with complex questions. Agentic RAG extends this paradigm by replacing…

The loop expansion is applied to a chiral effective hadronic lagrangian; with the techniques of Infrared Regularization, it is possible to separate out the short-range contributions and to write them as local products of fields that are…

Retrieval-augmented generation has gained significant attention due to its ability to integrate relevant external knowledge, enhancing the accuracy and reliability of the LLMs' responses. Most of the existing methods apply a dynamic…

We discuss some applications of the effective quantum field theory to the description of the physics beyond the Standard Model. We consider two different examples. In the first one we derive, at the one-loop level, an effective lagrangian…

We present several continued fraction algorithms, each of which gives an eventually periodic expansion for every quadratic element of ${\mathbb Q}_p$ over ${\mathbb Q}$ and gives a finite expansion for every rational number. We also give,…

Large Language Models (LLMs) have achieved strong performance across a wide range of natural language processing tasks in recent years, including machine translation, text generation, and question answering. As their applications extend to…

Constructions introduced by Dirac for singular Lagrangians are extended and reinterpreted to cover cases when kernel distributions are either nonintegrable or of nonconstant rank, and constraint sets need not be closed.

Large Language Models (LLMs) and Knowledge Graphs (KGs) offer a promising approach to robust and explainable Question Answering (QA). While LLMs excel at natural language understanding, they suffer from knowledge gaps and hallucinations.…