This decommissioned ERA site remains active temporarily to support our final migration steps to https://ualberta.scholaris.ca, ERA's new home. All new collections and items, including Spring 2025 theses, are at that site. For assistance, please contact erahelp@ualberta.ca.
Search
Skip to Search Results-
If It Ain’t Broke, Don’t Fix It: the Unintended Consequences of Large Language Model Code Repairs
Download2024-08-01
Nowadays, we heavily rely on ChatGPT to generate content, including writing code. But have you ever thought about the scenario where you input the correct content while GPT outputs a bug? This project aims to explore the unintended consequences of code repairs made by large language models. By...
-
Fall 2024
Table reasoning is a challenging task that requires understanding both natural language questions and structured tabular data. While Large Language Models (LLMs) have shown impressive capabilities in natural language understanding and generation, they often struggle with large tables due to their...
-
Item Difficulty and Response Time Prediction with Large Language Models: An Empirical Analysis of USMLE Items
Download2024-06-20
Bulut, O., Gorgun, G., Tan, B.
This paper summarizes our methodology and results for the BEA 2024 Shared Task. This competition focused on predicting item difficulty and response time for retired multiple-choice items from the United States Medical Licensing Examination® (USMLE®). We extracted linguistic features from the item...
-
Leveraging Large Language Models for Speeding Up Local Search Algorithms for Computing Programmatic Best Responses
DownloadFall 2024
Despite having advantages such as generalizability and interpretability over neural representations, programmatic representations of hypotheses and strategies face significant challenges. This is because algorithms writing programs encoding hypotheses for solving supervised learning problems and...