: "A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation" – A 2023 paper addressing gender bias specifically in machine translation.
: Critically examines gender biases in reference letters generated by LLMs like GPT. 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". : "A Tale of Pronouns: Interpretability Informs Gender
This 2023 paper by Wan et al. investigates how large language models (LLMs) may perpetuate social biases when writing recommendation letters. It is highly regarded for its systematic approach to examining language style and lexical content. This 2023 paper by Wan et al
: "How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models" – A study comparing pretrained multilingual models against monolingual ones.
Recommended Paper: "Gender Biases in LLM-Generated Reference Letters"
: 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)
No account yet?
Create an Account