← Search

Shucheng Zhu

2 accepted papers

2024

Evaluating Moral Beliefs across LLMs through a Pluralistic Framework

EMNLP 2024finding

Proper moral beliefs are fundamental for language models, yet assessing these beliefs poses a significant challenge. This study introduces a novel three-module framework to evaluate the moral beliefs of four prominent large language models. Initially, we constructed a dataset containing 472 moral ch…

2024

Quite Good, but Not Enough: Nationality Bias in Large Language Models - a Case Study of ChatGPT

COLING 2024main

While nationality is a pivotal demographic element that enhances the performance of language models, it has received far less scrutiny regarding inherent biases. This study investigates nationality bias in ChatGPT (GPT-3.5), a large language model (LLM) designed for text generation. The research cov…