Math RLHF
Compared LLM responses to a maths problem along multiple dimension (i.e. truthfulness, wording and conciseness) and corrected the solutions.
Hire this AI Trainer
Sign in or create an account to invite AI Trainers to your job.
No subject matter listed
I have strong experience in Reinforcement Learning with Human Feedback (RLHF) and Supervised Fine-Tuning (SFT) projects in German. I’ve also contributed to math, science, and STEM evaluation projects, where precision and subject-matter knowledge are essential for producing high-quality datasets. My key strengths include linguistic accuracy, attention to detail, and the ability to apply complex guidelines while handling edge cases. Combining language expertise with technical reasoning, I ensure the correctness and authenticity of outputs produced by LLMs.
Compared LLM responses to a maths problem along multiple dimension (i.e. truthfulness, wording and conciseness) and corrected the solutions.
Evaluated and commented texts by an LLM across a broad spectrum of topics on the basis of complex guidelines referring to types of texts, content and form.
Composed prompts for German texts up to 1000 words, rated said LLM texts along complex guidelines and rewrote when necessary.
Bachelor Materials Science, Materials Science and Engineering
AI Evaluator
Guest reception and hospitality