AUB ScholarWorks

Gender Bias Detection: Examining the Implicit Bias Inherited by ChatGPT

Show simple item record

dc.contributor.advisor Khreich, Wael Chazbeck, Jana 2024-02-15T07:01:37Z 2024-02-15T07:01:37Z 2024-02-15 2024-02-13
dc.description.abstract In this drastically evolving digital era, textual content production heavily relies on Large Language Models. These models are prone to inherit and thus propagate various forms of stereotypes and gender bias from their training corpus, which has harmful consequences on the worldwide population, such as loss of human potential, aggressive behaviors, biased mental imagery, and unfair labor force participation. Therefore, this thesis focused on evaluating gender bias in the responses of one of the most recent and popular LLMs, ChatGPT. We examined occupational and semantic bias in three common tasks of ChatGPT as well as in the embedding task of Ada-V2 model. After that, we finetuned ChatGPT on bias detection for three types of bias: sexism, dehumanization, and generic bias. The finetuned versions outperformed the original model as well as other popular LLMs in bias detection. We were also able to highlight two major weaknesses in ChatGPT’s learning capabilities as well as reduce the gender gaps in the model’s responses. This research built a strong basis for future work to ensure the safe and valuable use of recent AI tools like ChatGPT.
dc.language.iso en
dc.subject Gender Bias
dc.subject Large Language Models
dc.subject ChatGPT
dc.subject ADA-V2 Embedding
dc.subject Finetuning
dc.title Gender Bias Detection: Examining the Implicit Bias Inherited by ChatGPT
dc.type Thesis
dc.contributor.department Suliman S. Olayan School of Business
dc.contributor.faculty Suliman S. Olayan School of Business
dc.contributor.commembers Nasr, Walid
dc.contributor.commembers Taleb, Sirine MSBA
dc.contributor.AUBidnumber 202220292

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search AUB ScholarWorks


My Account