Postdoctoral Position on Socio-cultural Bias Detection in LLMs

Postdoctoral position at INRIA Paris, INRIA Chile, and Universidad de Chile to research socio-cultural bias detection in LLMs. Apply by June 1st, 2025.

A postdoctoral position is available at INRIA Paris, INRIA Chile, and Universidad de Chile to address cultural biases in Large Language Models (LLMs). The project aims to define sociologically grounded notions of social bias, detect biases through model behavior analysis, and apply fact-editing techniques to mitigate harmful stereotypes.

• Key responsibilities include developing techniques to ease the exploration and mitigation of socio-cultural biases.
• Creating new benchmarks to assess model sensitivity to culturally-based biases.
• Collaborating with the Almanach team and members from Universidad de Chile and Inria Chile.

For more information and to apply, visit the job posting. The deadline to apply is June 1st, 2025.

Tags: Postdoctoral Position, Socio-cultural Bias Detection, Large Language Models, LLMs, NLP, AI Research, Bias Mitigation