Researcher uses LLMs to analyze mock interview transcripts for bias studies
soumitrashukla9 · x · 2026-09-02
Soumitra Shukla discusses using LLMs to analyze mock interview transcripts as a proxy for real interview data to study hiring biases against non-elite candidates. LLMs allow for flexible, context-aware analysis of text that was previously inaccessible. However, Shukla notes that LLMs can't do everything; he personally called over 200 hiring managers to ground the study in reality.
More from Research
- Justin Johnson on World Models and the Future of Spatial AI — CSProfKGD · 2026-09-02
- Sebastian Raschka releases guide to build reasoning models from scratch — vboykis · 2026-09-02
- Stanford Releases Terminal-Bench-Science for AI Research Agents — AlexGDimakis · 2026-09-02
- Fei-Fei Li Praises World Labs' Camera-Conditioned World Model — drfeifei · 2026-09-02
- "Mathematics for AI" ranks 2nd on Amazon, adds PDE perspectives on deep learning — wufuheng · 2026-09-02
- Meta proposes AI Research Preference Models to help agents select high-value experiments — omarsar0 · 2026-09-02