arXiv subjects

Linh Huynh

Publications and source records attributed to Linh Huynh.

5 recordsLinked to original sources

arXiv2026

Learning Social Influence with Unobserved Attention

Social influence, the tendency of our social environment to sway our beliefs and behaviors, is often cited as a driver of population-level trends in opinions or beliefs. Many quantitative theories of social influence assume that an agent interacts with its entire social environment. This assumption is often unrealistic. For example, users of online platforms typically see posts from only a small subset of the accounts they follow at any given time. We introduce a simple probabilistic agent-based model of social influence that explicitly models unobserved attention mechanisms. The first of these latent mechanisms is selection: each agent interacts with only one other agent at a time from its social environment. The second is retention: the agent chooses whether or not to ignore the opinion of the other. Our model admits an efficient maximum-likelihood algorithm which allows us to fit it to opinion traces even when these mechanisms are unobserved. On synthetic data, omitting either latent mechanism reduces the overall strength of social influence governed by the inferred interaction kernel, which hides the evidence for the underlying nonlinearity of the social influence. We study a selection of previously analyzed empirical datasets and curate several new ones. We show that models that include the latent mechanisms are often more predictive on these datasets; indeed, they typically improve prediction far more than the choice of interaction kernel does. Modeling latent attention increases held-out predictive likelihood on 14 of these 15 datasets. Each mechanism changes the size of the inferred kernel in a predictable direction, while its effect on the kernel's shape depends on the data.

physics.soc-ph↗

arXiv2026

Human-AI Interaction Mediated by Courtship Language Culture: Computational Statistics and Probabilistic Modeling

Large language models are entering living cultural practices, including intimate ones. We study a collegiate courtship tradition at Dartmouth College called flitzing, the tradition of sending rhymed flirtatious emails to ask peers out, as a measurable microcosm of a culture absorbing artificial intelligence. We combine four sources of evidence: human evaluation surveys in two waves (2025 and 2026); information retrieval over 33 human-written and 5,610 AI-generated flitzes spanning 17 sampling temperatures; evaluation of the same survey by three generative language models; and simulation of a coupled multi-species bipartite spin glass model of people and texts. Four main findings emerge. First, sampling temperature induces a phase transition in diversity: below the transition, AI-generated flitzes are more homogeneous than the human, while above it they decohere, and human baselines of diversity remain stable across years, indicating persistent collective structure in human creativity. Second, human judges conflate perceived quality with human authorship, whereas AI judges detect provenance almost perfectly yet still rate human-written flitzes higher. Third, the transition window, with temperature between 1.25 and 1.38, is consistent across biased survey data, unbiased text statistics, and the mathematical model, which also reproduces the observed clustering. Fourth, detection ability generalizes beyond the local culture, with Dartmouth and non-Dartmouth respondents performing comparably, and strengthens over time, with 2026 respondents above chance at every temperature. We conclude that AI participation in a tight cultural genre is regime dependent: conformist and homogenizing below criticality, detectable and disruptive above it.

physics.soc-ph↗

arXiv2026

Cognitively Diverse Multiple-Choice Question Generation: A Hybrid Multi-Agent Framework with Large Language Models

Recent advances in large language models (LLMs) have made automated multiple-choice question (MCQ) generation increasingly feasible; however, reliably producing items that satisfy controlled cognitive demands remains a challenge. To address this gap, we introduce ReQUESTA, a hybrid, multi-agent framework for generating cognitively diverse MCQs that systematically target text-based, inferential, and main idea comprehension. ReQUESTA decomposes MCQ authoring into specialized subtasks and coordinates LLM-powered agents with rule-based components to support planning, controlled generation, iterative evaluation, and post-processing. We evaluated the framework in a large-scale reading comprehension study using academic expository texts, comparing ReQUESTA-generated MCQs with those produced by a single-pass GPT-5 zero-shot baseline. Psychometric analyses of learner responses assessed item difficulty and discrimination, while expert raters evaluated question quality across multiple dimensions, including topic relevance and distractor quality. Results showed that ReQUESTA-generated items were consistently more challenging, more discriminative, and more strongly aligned with overall reading comprehension performance. Expert evaluations further indicated stronger alignment with central concepts and superior distractor linguistic consistency and semantic plausibility, particularly for inferential questions. These findings demonstrate that hybrid, agentic orchestration can systematically improve the reliability and controllability of LLM-based generation, highlighting workflow design as a key lever for structured artifact generation beyond single-pass prompting.

cs.CL↗

arXiv2025

Inferring birth versus death dynamics for ecological interactions in stochastic heterogeneous populations

In this paper, we study the significance of ecological interactions and separation of birth and death dynamics in stochastic heterogeneous populations via general birth-death processes. Interactions can manifest through the birth dynamics, the death dynamics, or some combination of the two. The underlying microscopic mechanisms are important but often implicit in population-level data. We propose an inference method for disambiguating the types of interaction and the birth and death processes from population size time series data of a stochastic $n$-type heterogeneous population. The interspecies interactions considered can be competitive, antagonistic, or mutualistic. We show that different pairs of birth and death rates with the same net growth rate result in different time series statistics. Then, the inference method is validated in the example of a birth-death process inspired by the two-type Lotka-Volterra interaction dynamics. Utilizing stochastic fluctuations enables us to estimate additional parameters in this stochastic Lotka-Volterra model, which are not identifiable in a deterministic model.

q-bio.PE↗

arXiv2022

Inferring Density-Dependent Population Dynamics Mechanisms through Rate Disambiguation for Logistic Birth-Death Processes

Density dependence is important in the ecology and evolution of microbial and cancer cells. Typically, we can only measure net growth rates, but the underlying density-dependent mechanisms that give rise to the observed dynamics can manifest in birth processes, death processes, or both. Therefore, we utilize the mean and variance of cell number fluctuations to separately identify birth and death rates from time series that follow stochastic birth-death processes with logistic growth. Our method provides a novel perspective on stochastic parameter identifiability, which we validate by analyzing the accuracy in terms of the discretization bin size. We apply our method to the scenario where a homogeneous cell population goes through three stages: (1) grows naturally to its carrying capacity, (2) is treated with a drug that reduces its carrying capacity, and (3) overcomes the drug effect to restore its original carrying capacity. In each stage, we disambiguate whether it happens through the birth process, death process, or some combination of the two, which contributes to understanding drug resistance mechanisms. In the case of limited data sets, we provide an alternative method based on maximum likelihood and solve a constrained nonlinear optimization problem to identify the most likely density dependence parameter for a given cell number time series. Our methods can be applied to other biological systems at different scales to disambiguate density-dependent mechanisms underlying the same net growth rate.

q-bio.PE↗