Read original ↗

newsMIT Technology Review AITrust 88 · LabPublished 26d agoLive · 24d ago

AI is more likely than humans to form biases when hiring

The next time you apply for a job, AI may screen your résumé before any human sees it. But there’s good reason to question whether AI will judge you fairly. Researchers already know that LLMs pick up human biases from their training data. New research suggests that LLMs can also develop their own biases from…

Research MIT Technology Review AI verified

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

PossiblePossibly related (embedding) · 48%Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias →
PossiblePossibly related (embedding) · 46%Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings →
PossiblePossibly related (embedding) · 50%Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning →

Covers

paperInside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias paperPrompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings

Covers (incoming)

paperUnlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning

Related across the graph

paperInside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias paperUnlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning paperPrompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings