Related papers: Confronting new physics theories to LHC data with …
The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated…
Convex analysis is a modern branch of mathematics with many applications. As Large Language Models (LLMs) start to automate research-level math and sciences, it is important for LLMs to demonstrate the ability to understand and reason with…
The new simulation for the ATLAS detector at LHC is performed using Geant4 in a complete OO/C++ environment. In this framework the simulation of the various test beams for the different ATLAS subdetectors offers an excellent opportunity to…
Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis. Despite this, existing benchmarks typically focus only on extracting text and simple layout information, neglecting the complex…
In this new era of large data, it is important to make sure we do not miss any signs of new physics. Using the publicly-available open data collected by the arXiv.org experiment in the \texttt{hep-ph} channel, corresponding to a raw total…
The complementarity between results anticipated from SuperB with those from the LHC experiments is discussed here. SuperB can contribute to searches for new physics using indirect constraints via precision tests of the standard model. In…
The ATLAS potential for the study of the top quark properties and physics beyond the Standard Model in the top quark sector, is described. The measurements of the top quark charge, the spin and spin correlations, the Standard Model decay…
While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…
This note describes the validation of material allowing the reinterpretation of an ATLAS search for decays of pair-produced neutral long-lived particles decaying in the hadronic part of the calorimeter, or at the edge of the electromagnetic…
This paper introduces a comprehensive system for detecting hallucinations in large language model (LLM) outputs in enterprise settings. We present a novel taxonomy of LLM responses specific to hallucination in enterprise applications,…
As artificial intelligence (AI) gains greater adoption in a wide variety of applications, it has immense potential to contribute to mathematical discovery, by guiding conjecture generation, constructing counterexamples, assisting in…
A novel model of the data selection, acquisition and analysis for a multi-purpose and multi-component high-energy-physics experiment is presented. Its departure point is the freedom and the responsibility given to the different physics…
Machine Reading Comprehension (MRC) is the task of answering a question over a paragraph of text. While neural MRC systems gain popularity and achieve noticeable performance, issues are being raised with the methodology used to establish…
Learning Analytics Dashboards can be a powerful tool to support self-regulated learning in Digital Learning Environments and promote development of meta-cognitive skills, such as reflection. However, their effectiveness can be affected by…
Person reidentification (re-ID) has been receiving increasing attention in recent years due to its importance for both science and society. Machine learning and particularly Deep Learning (DL) has become the main re-id tool that allowed…
This paper explores the potential of Large Language Models to accurately extract and translate equations from typed student responses into a standard format. This is a useful task as standardized equations can be graded reliably using a…
Most proposals in the anomaly detection field focus exclusively on the detection stage, specially in the recent deep learning approaches. While providing highly accurate predictions, these models often lack transparency, acting as "black…
The standard model of particle physics is an extremely successful theory of fundamental interactions, but it has many known limitations. It is therefore widely believed to be an effective field theory that describes interactions near the…
Meta-learning is used to efficiently enable the automatic selection of machine learning models by combining data and prior knowledge. Since the traditional meta-learning technique lacks explainability, as well as shortcomings in terms of…
With the rapid advancement of Large Language Models (LLMs), there is an increasing need for challenging benchmarks to evaluate their capabilities in handling complex tabular data. However, existing benchmarks are either based on outdated…