HalluWorld is a controlled benchmark using explicit reference world models to automatically label and disentangle hallucinations in LLMs across synthetic environments with varying complexity and observability.
hub
Perry, Matthew R
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
fields
astro-ph.HE 1 astro-ph.IM 1 cond-mat.mtrl-sci 1 cs.AI 1 cs.CL 1 cs.CY 1 cs.LG 1 cs.LO 1 gr-qc 1 nucl-th 1roles
background 3polarities
background 3representative citing papers
ATLAS introduces an LLM-orchestrated agentic framework for dynamic test-time scaling via extensible 'explore' actions, achieving higher accuracy with fewer API calls than fixed-workflow baselines on four benchmarks.
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
Rydberg-atom electric field sensor using sapphire cell enables off-resonant detection of sub-100 MHz RF signals via AC Stark shifts, with sensitivity and dynamic range reported at ISM frequencies plus shared optimization code.
Unified AMD analysis constrains nuclear symmetry energy at 0.28 saturation density to 13.84 ± 1.31 MeV via combined neutron-skin and dipole polarizability data.
Reevaluation of 610 FSRQ candidates shows most radio spectra are flat within per-source uncertainties but 60% of well-covered sources exhibit restarted-peaked morphologies, indicating the flat-spectrum label is insufficient and BZQ better captures the diversity.
Single-diffractive cross sections in pp and pbar p collisions are described by a three-parameter fit in a dephasing Lindblad framework yielding a consistent decoherence factor φ ≈ 0.89 that favors CPT-invariant dephasing over CP-invariant.
The paper presents a conceptual design for a stacked focal-plane polarimeter using multilayer mirrors, imaging photoelectric detectors, and an active Compton polarimeter to extend X-ray polarimetry to tens of keV with improved sensitivity.
Authors propose a four-stage framework to analyze opportunities and risks of generative AI across the health information journey from public sources to clinical care.
Theoretical calculations explain experimental magnetoelastic data in antiferromagnetic MnPt, linking magnetic structure to anisotropy energy and isotropic/anisotropic magnetostriction coefficients.
A review summarizing formation-channel predictions, waveform effects, and population-level constraints on stellar-mass black hole spins from the first decade of gravitational-wave observations.
citing papers explorer
-
AlphaEvolve: A coding agent for scientific and algorithmic discovery
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
-
Magnetoelasticity - magnetic structure interrelation - tetragonal MnPt system study
Theoretical calculations explain experimental magnetoelastic data in antiferromagnetic MnPt, linking magnetic structure to anisotropy energy and isotropic/anisotropic magnetostriction coefficients.