Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution — mentioned by skupig

Thu, 04 Jun 2026 17:05:27 GMT

There has been plenty of research that shows LLMs encode social biases. It seems pretty obvious even before looking at the research that training on the whole internet will end up encoding widely-held social biases and stereotypes. https://arxiv.org/pdf/2508.07111 https://github.com/angl1n/social-bias-llm-vlm

Paper and discussion history. A mention is not an endorsement.

Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution · HackerPapers discussions

Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution — mentioned by skupig