Online Archive of University of Virginia Scholarship
LLM Threat Query - Improving LLM KQL Generation; Bridging Actors And Accountability In AI Driven Misinformation Using Actor Network Theory; Earthquake Analysis And Prediction: Comparing ETAS And USGS Earthquake Data139 views
Author
Kamalakrishnan, Vishal, School of Engineering and Applied Science, University of Virginia
Advisors
Fox, Geoffrey, PV-BII-Biocomplexity Initiative, University of Virginia
Abstract
Technical Report
Earthquakes pose a significant threat to human lives and infrastructure, providing a need for accurate earthquake forecasting models to help mitigate risk. My capstone research project presents a comprehensive analysis comparing synthetic earthquake simulations generated by the Epidemic-Type Aftershock Sequence (ETAS) model with historical earthquake records from the United States Geological Survey (USGS) spanning 1960 to 2023. I found discrepancies between modeled and observed data by analyzing patterns and energy related to significant earthquakes (magnitude ≥ 6.5). Notably, ETAS simulated data shows higher average energy levels before and after major earthquakes, while USGS data indicates a considerable energy spike just before the main event, which is not observed in ETAS data.
STS Prospectus & Research Paper
My STS research paper examines Air Canada’s 2024 chatbot failure through ANT and argues that the chatbot’s failure was a result of its actor-network rather than an isolated technical error. It examined several factors within Air Canada’s network that contributed to this failure including corporate strategy, industry trends, cheaper GPU access, and legal ambiguities and accountability. The technical project presented in the Prospectus develops a framework to improve the accuracy of Large Language Model (LLM) queries in generating Kusto Query Language (KQL) queries. Working on both projects simultaneously enhanced my understanding of AI products and failures in their implementation. The technical project allowed me to focus on combating AI hallucinations from a technical perspective, enriched by insights from STS research, which shows how socio-technical dynamics shape technical design.
Note: technical project referenced is LLM Threat Query that I have been working on during fall 2024 - spr 2025 which is unrelated to my capstone research - Earthquake Analysis And Prediction, that I completed during spr 2024.
Degree
BS (Bachelor of Science)
Language
English
Rights
All rights reserved (no additional license for public reuse)
Kamalakrishnan, Vishal. LLM Threat Query - Improving LLM KQL Generation; Bridging Actors And Accountability In AI Driven Misinformation Using Actor Network Theory; Earthquake Analysis And Prediction: Comparing ETAS And USGS Earthquake Data. University of Virginia, School of Engineering and Applied Science, BS (Bachelor of Science), 2025-05-05, https://doi.org/10.18130/ratx-m959.
