Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–5 of 5 results for author: Boros, I

.
  1. arXiv:2607.00895  [pdf, ps, other

    cs.CL

    Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents

    Authors: Ádám Kovács, Bowei He, Xue Liu, István Boros, Szilveszter Tóth, Gábor Recski

    Abstract: Hallucination detection for retrieval-augmented generation (RAG) is usually evaluated on natural-language document evidence. However, grounded generation systems increasingly rely on structured inputs: source code, developer-tool output, markdown documents, tables, and repository metadata. We introduce a unified benchmark for span-level hallucination detection over code, tool output, structured do… ▽ More

    Submitted 1 July, 2026; originally announced July 2026.

    Comments: 8 pages

  2. arXiv:2606.10950  [pdf, ps, other

    physics.ins-det nucl-ex

    Feasibility demonstration of continuous signal-based neutron noise measurements by experiments and simulations

    Authors: Máté István Boros, Máté Szieberth, Gergely Klujber, Imre Pázsit, István Barth, Yasunori Kitamura, Tsuyoshi Misawa

    Abstract: Neutron noise methods are used to determine kinetic parameters such as the prompt neutron decay constant, but traditional pulse-counting suffers from dead-time and pile-up at high detection rates. Recent theory shows that analysing the continuous detector current can avoid these limitations if pulse-shape effects are properly treated. This work presents a feasibility study of continuous-signal neu… ▽ More

    Submitted 9 June, 2026; originally announced June 2026.

    Comments: Manuscript submitted to Progress in Nuclear Energy

  3. arXiv:2605.21102  [pdf, ps, other

    cs.CL cs.AI cs.SE

    ACL-Verbatim: hallucination-free question answering for research

    Authors: Gábor Recski, Szilveszter Tóth, Nadia Verdha, István Boros, Ádám Kovács

    Abstract: Academic researchers need efficient and reliable methods for collecting high-quality information from trusted sources, but modern tools for AI-assisted research still suffer from the tendency of Large Language Models (LLMs) to produce factually inaccurate or nonsensical output, commonly referred to as hallucinations. We apply the extractive question answering system VerbatimRAG to research papers… ▽ More

    Submitted 20 May, 2026; originally announced May 2026.

    Comments: 13 pages

  4. arXiv:1911.10774  [pdf, ps, other

    cs.CE math.NA physics.comp-ph physics.geo-ph

    Benchmark for numerical solutions of flow in heterogeneous groundwater formations

    Authors: Cristian D. Alecsa, Imre Boros, Florian Frank, Peter Knabner, Mihai Nechita, Alexander Prechtel, Andreas Rupp, Nicolae Suciu

    Abstract: This article presents numerical investigations on accuracy and convergence properties of several numerical approaches for simulating steady state flows in heterogeneous aquifers. Finite difference, finite element, discontinuous Galerkin, spectral, and random walk methods are tested on one- and two-dimensional benchmark flow problems. Realizations of log-normal hydraulic conductivity fields are gen… ▽ More

    Submitted 3 March, 2020; v1 submitted 25 November, 2019; originally announced November 2019.

    Comments: Extended version of the published paper

    MSC Class: 65N06

  5. arXiv:1904.12952  [pdf, ps, other

    cs.LG math.OC stat.ML

    New optimization algorithms for neural network training using operator splitting techniques

    Authors: Cristian Daniel Alecsa, Titus Pinta, Imre Boros

    Abstract: In the following paper we present a new type of optimization algorithms adapted for neural network training. These algorithms are based upon sequential operator splitting technique for some associated dynamical systems. Furthermore, we investigate through numerical simulations the empirical rate of convergence of these iterative schemes toward a local minimum of the loss function, with some suitab… ▽ More

    Submitted 21 March, 2020; v1 submitted 29 April, 2019; originally announced April 2019.

    Comments: 21 pages, 6 tables, 7 figures