Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
OneFormaNo subject matter listed
Image
TextI have hands-on experience at the entry level evaluating large language model (LLM) outputs in Norwegian, focusing on aspects such as groundedness, comprehensiveness, composition, and the potential harmfulness of AI-generated responses. As part of my work, I provide written justifications for each rating, contributing to reinforcement learning from human feedback (RLHF) and helping to ensure both model quality and safety. With a strong academic background in sociology and advanced training in quantitative analysis, I bring a critical and nuanced perspective to language data. My multilingual skills (Norwegian, English, and French), combined with experience assessing both AI-generated text and images, enable me to contribute to a wide range of annotation and evaluation tasks with precision and contextual sensitivity.
The project included evaluating AI-generated images and emojis for overall quality and appropriateness.
This project involved evaluating AI-generated responses in Norwegian using Centific’s internal grading platform. Tasks included rating model outputs based on groundedness, comprehensiveness, composition, and safety. Each rating was accompanied by a written explanation.
Doctor of Philosophy (submitted; under consideration), Sociology and criminology
Master's Degree, Sociology And Political Philosophy
Freelance Journalist
Content Specialist
