Related papers: Improving Gamma-ray Source Search with Image Proce…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating up-to-date external knowledge, yet real-world web environments present unique challenges. These limitations manifest as two key challenges: pervasive…

In its first four years of operation, the Fermi Large Area Telescope (LAT) detected 3033 $\gamma$-ray emitting sources. In the Fermi-LAT Third Source Catalogue (3FGL) about 50% of the sources have no clear association with a likely…

Using a series of detector measurements taken at different locations to localize a source of radiation is a well-studied problem. The source of radiation is sometimes constrained to a single point-like source, in which case the location of…

In this chapter, we consider generative information retrieval evaluation from two distinct but interrelated perspectives. First, large language models (LLMs) themselves are rapidly becoming tools for evaluation, with current research…

The spatial extension of a gamma-ray source is an essential ingredient to determine its spectral properties as well as its potential multi-wavelength counterpart. The capability to spatially resolve gamma-ray sources is greatly improved by…

Point source localisation is generally modelled as a Lasso-type problem on measures. However, optimisation methods in non-Hilbert spaces, such as the space of Radon measures, are much less developed than in Hilbert spaces. Most numerical…

We report an extension of the source imaging method for analyzing three-dimensional sources from three-dimensional correlations. Our technique consists of expanding the correlation data and the underlying source function in spherical…

Retrieval-Augmented Generation (RAG) is a powerful approach that enables large language models (LLMs) to incorporate external knowledge. However, evaluating the effectiveness of RAG systems in specialized scenarios remains challenging due…

Unassociated Fermi-LAT sources provide a population with discovery potential. We discuss efforts to find new source associations for this population, and summarize the successes to date. We discuss how the measured gamma-ray properties of…

We present a new catalog of high-redshift candidate \textit{Herschel} sources. Our sample is obtained after applying a multifrequency filtering method ("matched multifilter"), which is designed to improve the signal-to-noise ratio (S/N) of…

Large language models (LLMs) achieve remarkable performance across domains but remain prone to hallucinations and inconsistencies. Retrieval-augmented generation (RAG) mitigates these issues by augmenting model inputs with relevant…

Employing the 12 NaI detectors in the Fermi GBM, the Earth Occultation Technique (EOT) can be used to measure the fluxes of x-ray and gamma-ray sources. Each time a source passes behind the Earth (or emerges from behind the Earth), a…

The second Fermi-LAT source catalog (2FGL) is the deepest all-sky survey available in the gamma-ray band. It contains 1873 sources, of which 576 remain unassociated. Machine-learning algorithms can be trained on the gamma-ray properties of…

Investigative journalists routinely confront large document collections. Large language models (LLMs) with retrieval-augmented generation (RAG) capabilities promise to accelerate the process of document discovery, but newsroom adoption…

Retrieval-Augmented Generation (RAG) enhances LLM factuality, yet design guidance remains English-centric, limiting insights for morphologically rich languages like Turkish. We address this by constructing a comprehensive Turkish RAG…

We present the Brera Multi-scale Wavelet ROSAT HRI source catalogue (BMW-HRI) derived from all ROSAT HRI pointed observations with exposure time longer than 100 s available in the ROSAT public archives. The data were analyzed automatically…

The effectiveness of Large Language Models (LLMs) in generating accurate responses relies heavily on the quality of input provided, particularly when employing Retrieval Augmented Generation (RAG) techniques. RAG enhances LLMs by sourcing…

Leveraging both labeled (input-output associations) and unlabeled data (wider contextual grounding) may provide complementary benefits in retrieval augmented generation (RAG). However, effectively combining evidence from these heterogeneous…

Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet models often generate outputs inconsistent with retrieved content. Accurate hallucination detection requires disentangling the contributions…

The retrieval-augmented generation (RAG) enables retrieval of relevant information from an external knowledge source and allows large language models (LLMs) to answer queries over previously unseen document collections. However, it was…