arXiv subjects

Shannon Gallagher

Publications and source records attributed to Shannon Gallagher.

5 recordsLinked to original sources

arXiv2026

Interpretable Stylistic Variation in Human and LLM Writing Across Genres, Models, and Decoding Strategies

Large Language Models (LLMs) are now capable of generating highly fluent, human-like text. They enable many applications, but also raise concerns such as large scale spam, phishing, or academic misuse. While much work has focused on detecting LLM-generated text, only limited work has gone into understanding the stylistic differences between human-written and machine-generated text. In this work, we perform a large scale analysis of stylistic variation across human-written text and outputs from 11 LLMs spanning 8 different genres and 4 decoding strategies using Douglas Biber's set of lexicogrammatical and functional features. Our findings reveal insights that can guide intentional LLM usage. First, key linguistic differentiators of LLM-generated text seem robust to generation conditions (e.g., prompt settings to nudge them to generate human-like text, or availability of human-written text to continue the style); second, genre exerts a stronger influence on stylistic features than the source itself; third, chat variants of the models generally appear to be clustered together in stylistic space, and finally, model has a larger effect on the style than decoding strategy, with some exceptions. These results highlight the relative importance of model and genre over prompting and decoding strategies in shaping the stylistic behavior of machine-generated text.

cs.CL↗

arXiv2025

Fine-Tuning LLMs for Report Summarization: Analysis on Supervised and Unsupervised Data

We study the efficacy of fine-tuning Large Language Models (LLMs) for the specific task of report (government archives, news, intelligence reports) summarization. While this topic is being very actively researched - our specific application set-up faces two challenges: (i) ground-truth summaries maybe unavailable (e.g., for government archives), and (ii) availability of limited compute power - the sensitive nature of the application requires that computation is performed on-premise and for most of our experiments we use one or two A100 GPU cards. Under this set-up we conduct experiments to answer the following questions. First, given that fine-tuning the LLMs can be resource intensive, is it feasible to fine-tune them for improved report summarization capabilities on-premise? Second, what are the metrics we could leverage to assess the quality of these summaries? We conduct experiments on two different fine-tuning approaches in parallel and our findings reveal interesting trends regarding the utility of fine-tuning LLMs. Specifically, we find that in many cases, fine-tuning helps improve summary quality and in other cases it helps by reducing the number of invalid or garbage summaries.

cs.CL↗

arXiv2024

Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning

Machine learning models are vulnerable to adversarial attacks, including attacks that leak information about the model's training data. There has recently been an increase in interest about how to best address privacy concerns, especially in the presence of data-removal requests. Machine unlearning algorithms aim to efficiently update trained models to comply with data deletion requests while maintaining performance and without having to resort to retraining the model from scratch, a costly endeavor. Several algorithms in the machine unlearning literature demonstrate some level of privacy gains, but they are often evaluated only on rudimentary membership inference attacks, which do not represent realistic threats. In this paper we describe and propose alternative evaluation methods for three key shortcomings in the current evaluation of unlearning algorithms. We show the utility of our alternative evaluations via a series of experiments of state-of-the-art unlearning algorithms on different computer vision datasets, presenting a more detailed picture of the state of the field.

cs.LG↗

arXiv2020

Exploring the nuances of R0: Eight estimates and application to 2009 pandemic influenza

For nearly a century, the initial reproduction number (R0) has been used as a one number summary to compare outbreaks of infectious disease, yet there is no `standard' estimator for R0. Difficulties in estimating R0 arise both from how a disease transmits through a population as well as from differences in statistical estimation method. We describe eight methods used to estimate R0 and provide a thorough simulation study of how these estimates change in the presence of different disease parameters. As motivation, we analyze the 2009 outbreak of the H1N1 pandemic influenza in the USA and compare the results from our eight methods to a previous study. We discuss the most important aspects from our results which effect the estimation of R0, which include the population size, time period used, and the initial percent of infectious individuals. Additionally, we discuss how pre-processing incidence counts may effect estimates of R0. Finally, we provide guidelines for estimating point estimates and confidence intervals to create reliable, comparable estimates of R0.

q-bio.PE↗

arXiv2017

SPEW: Synthetic Populations and Ecosystems of the World

Agent-based models (ABMs) simulate interactions between autonomous agents in constrained environments over time. ABMs are often used for modeling the spread of infectious diseases. In order to simulate disease outbreaks or other phenomena, ABMs rely on "synthetic ecosystems," or information about agents and their environments that is representative of the real world. Previous approaches for generating synthetic ecosystems have some limitations: they are not open-source, cannot be adapted to new or updated input data sources, and do not allow for alternative methods for sampling agent characteristics and locations. We introduce a general framework for generating Synthetic Populations and Ecosystems of the World (SPEW), implemented as an open-source R package. SPEW allows researchers to choose from a variety of sampling methods for agent characteristics and locations when generating synthetic ecosystems for any geographic region. SPEW can produce synthetic ecosystems for any agent (e.g. humans, mosquitoes, etc), provided that appropriate data is available. We analyze the accuracy and computational efficiency of SPEW given different sampling methods for agent characteristics and locations and provide a suite of diagnostics to screen our synthetic ecosystems. SPEW has generated over five billion human agents across approximately 100,000 geographic regions in about 70 countries, available online.

stat.OT↗