gender bias
PulseAugur coverage of gender bias — every cluster mentioning gender bias across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Answer format significantly impacts gender bias measurement in LLMs, study finds
A new study published on arXiv investigates how variations in answer formats affect the measurement of gender bias in large language models. Researchers found that changing the format from closed-ended to Likert-scaled …
-
New research analyzes gender bias mechanisms in dense retrieval models
A new research paper published on arXiv details a mechanistic analysis of gender bias in dense retrieval models. The study identifies that gender sensitivity originates in input embeddings and is amplified by specific a…
-
New white-box auditing method reveals hidden LLM biases
Researchers have developed a new framework for auditing large language models (LLMs) that goes beyond traditional black-box testing. This white-box approach utilizes activation steering to examine the model's internal w…
-
AI stories show masculine bias, neutrality may erase identities
A new research paper titled "Neutrality Bites: Gender Representation in AI-Generated Animal Stories" reveals a significant masculine bias in large language models when generating narratives. Despite efforts to mitigate …
-
Study finds PCA debiasing distorts word embedding geometry
A new study published on arXiv analyzes Principal Component Analysis (PCA)-based methods for debiasing gender bias in word embeddings. The research reveals that while direct gender bias is often concentrated in the firs…
-
Chain-of-Thought prompting shows superficial bias reduction in LLMs
A new research paper explores the effectiveness of Chain-of-Thought (CoT) prompting in mitigating gender bias in large language models (LLMs). The study found that while CoT prompting can superficially balance biased be…
-
Dutch BERT model exhibits persistent gender bias despite explicit cues
A new study on a Dutch BERT model reveals persistent gender bias, even when explicit cues contradict learned associations. Researchers found that the model struggled to override stereotypical gender-profession pairings,…