<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T01:19:22Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/33296" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/33296</identifier><datestamp>2026-06-26T07:07:22Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Fei, Chiang</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Yaxuan Chen</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department">Computing and Software</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-06-25T19:36:49Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2026</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/11375/33296</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/158</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">Large language models (LLMs) have increasingly been used in data preparation pipelines due to their strong natural language understanding and reasoning capabilities. Data preparation tasks such as entity matching, and missing value imputation often rely on identifying syntactic patterns in the data, and domain-specific, contextual interpretations, the latter being a differentiating strength of LLM-based systems. However, these systems are imperfect demonstrating biases and inaccuracies. Studies have shown that 42\% of model-centric approaches lead to inaccuracies and hallucinations, and 40\% of models suffer from biases due to incomplete data. Existing work has studied LLM-based data preparation under fixed prompts and parameter configurations. In this paper, we present a systematic, comparative evaluation of LLM-driven entity matching, missing value imputation, and semantic reasoning across four state-of-the-art models. We evaluate the impact of various parameters including training example quantity, class ratios, input record lengths, missing values proportions, and the utility of key attribute values. Our results show the sensitivities and performance of these models using a suite of real data collections.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree">Master of Science (MSc)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="rights" lang="en">Attribution 4.0 International</dim:field>
   <dim:field mdschema="dc" element="rights" qualifier="uri">http://creativecommons.org/licenses/by/4.0/</dim:field>
   <dim:field mdschema="dc" element="subject">data preparation</dim:field>
   <dim:field mdschema="dc" element="subject">data-centric AI</dim:field>
   <dim:field mdschema="dc" element="subject">data cleaning</dim:field>
   <dim:field mdschema="dc" element="title">Evaluation of LLM-driven Data Preparation</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>