243 Mp4 File

: Uses social science-inspired evaluation methods to track bias propagation across language style and lexical content. Resources : Read the Full Paper (PDF) Watch the Presentation (243.mp4) (Direct Video Link) Other Related Papers (Index 243)

: "A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation" – A 2023 paper addressing gender bias specifically in machine translation. 243 mp4

: The authors found that LLMs often use different descriptive terms based on gender—for example, describing female candidates as "warm" while calling male candidates "role models". : Uses social science-inspired evaluation methods to track

: "How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models" – A study comparing pretrained multilingual models against monolingual ones. 243 mp4

Recommended Paper: "Gender Biases in LLM-Generated Reference Letters"