A GNN trained on bipartite alignment graphs between references and LLM generations reports state-of-the-art hallucination detection across four datasets, beating prior methods and GPT-4o.
Princeton University Press
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
The authors extend Forman's combinatorial differential forms with operators for scalar variables to enable intrinsic, dimension-dependent modeling of diffusion in discrete complexes.
Order is distinct from control, where control is defined as a local receiver-gated response law demonstrated across biological circuits and LLM response panels with reported prediction accuracies of 72-84%.
Generalizing two DPP-based Monte Carlo estimators to continuous domains provides variance rates of O(N^{-(1+1/d)}) for a fixed DPP method and O(1/N) for a tailored DPP method, along with new sampling algorithms.
Content moderation operates as a stochastic penal colony that banishes users through the constant threat of account suspension, shown via auto-ethnographic case studies of Twitter, OpenAI DALL-E 2, and Pinterest.
Correct application of the Engle-Granger test to levels shows no cointegrating relationship between US job vacancies and southwest border crossings, invalidating Bahar (2025)'s estimates.
A time-varying aggregate efficiency converts the energy-GDP relation into a general thermodynamic model that corrects earlier claims of a constant 50-year link and reveals a 1970 historical minimum.
A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.
citing papers explorer
-
Graph Alignment Topology as an Inductive Bias for Grounding Detection
A GNN trained on bipartite alignment graphs between references and LLM generations reports state-of-the-art hallucination detection across four datasets, beating prior methods and GPT-4o.
-
Diffusion in multi-dimensional solids using Forman's combinatorial differential forms
The authors extend Forman's combinatorial differential forms with operators for scalar variables to enable intrinsic, dimension-dependent modeling of diffusion in discrete complexes.
-
Order Is Not Control
Order is distinct from control, where control is defined as a local receiver-gated response law demonstrated across biological circuits and LLM response panels with reported prediction accuracies of 72-84%.
-
On two ways to use determinantal point processes for Monte Carlo integration
Generalizing two DPP-based Monte Carlo estimators to continuous domains provides variance rates of O(N^{-(1+1/d)}) for a fixed DPP method and O(1/N) for a tailored DPP method, along with new sampling algorithms.
-
Mapping the Stochastic Penal Colony
Content moderation operates as a stochastic penal colony that banishes users through the constant threat of account suspension, shown via auto-ethnographic case studies of Twitter, OpenAI DALL-E 2, and Pinterest.
-
US labor market conditions and migration: a reassessment of Bahar (2025)
Correct application of the Engle-Granger test to levels shows no cointegrating relationship between US job vacancies and southwest border crossings, invalidating Bahar (2025)'s estimates.
-
A new monetary metric is found in the thermodynamic relation between energy and GDP
A time-varying aggregate efficiency converts the energy-GDP relation into a general thermodynamic model that corrects earlier claims of a constant 50-year link and reveals a 1970 historical minimum.
-
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.