Open-weight large language models are increasingly used in
education, hiring, and information-seeking contexts that
touch neurodivergent people, yet we lack a clear empirical
map of how their portrayals of neurodiversity shift under
everyday prompt variation. We present a multi-condition,
multi-model audit of LLM portr...
Carlos Toxtli, M. Delaflor· Proceedings of the AAAI/ACM...· 0 citations
This workshop aims to gather creative workers in gaming broadly to exchange knowledge on opportunities and challenges of generative AI and collaboratively envision how generative AI should be designed to support their future creative work and gaming as a broad creative domain while mitigating AI’s potential risks and l...
Guo Freeman, Carlos Toxtli, Ruchi Panchanadikar et al.· Companion Proceedings of the...· 0 citations
Researchers increasingly use large language models (LLMs) to revise manuscripts in response to peer reviews, yet this adoption is largely unprincipled and risks the ironies of automation. Prompt-Level Supervisory Alignment (PLSA) applies Supervisory Control Theory as a structured prompting strategy for LLM-assisted man...
Wangfan Li, Sofia Abilene Campos Hernandez, Carlos Toxtli· Proceedings of the Human Fac...· 0 citations
Effective human-agent cooperation requires that users form mental models of an agent’s behavioral tendencies. Yet LLM-based virtual agents are inherently stochastic, undermining the behavioral consistency that mental model formation depends on. We introduce the Constraint-Entropy Tradeoff (CET) model, an information-th...
Carlos Toxtli, M. Delaflor· Proceedings of the 26th ACM...· 0 citations
Spectral co-clustering is a useful tool for discovering latent structure in word-document matrices, but its reliance on singular value decomposition (SVD) can make standard formulations expensive on high-dimensional data. This paper presents two randomized approximations for normalized spectral co-clustering of biparti...
Evaluating a diverse panel of contemporary models under three administration protocols, it is shown that a naive harness, with a fixed token budget and an unaudited parser, manufactures failing workers out of competent ones, misreading a model that answers essentially every item correctly as badly inaccurate, answer-bi...
Carlos Toxtli, M. Delaflor· Proceedings of the 2026 ACM...· 0 citations
TREAT is introduced, a benchmark for evaluating whether large language models can recover known theorem identities from equivalence-preserving formula-level transformations, and provides a controlled testbed for evaluating representation-robust access to formal knowledge.
Evaluating state-of-the-art open LLMs reveals a significant robustness gap, and shows that reliable process-level verification remains challenging, and evaluator robustness should be measured separately from solver accuracy, even in a simple algebraic domain with exact ground truth.
Crop modelling is essential for agricultural water management but often relies on simplified water balance routines that limit representation of soil moisture dynamics. To address this limitation, we developed a coupled model that integrates the 1‐D Richards equation, solved using a finite difference method into th...
Krishna Panthi, Vidya S. Samadi, Carlos Toxtli· Irrigation and Drainage· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
