RLHF Preference Ranking & Fact-Checking for LLM Alignment
TextText Generation
In this role, I served as a Subject Matter Expert to align Large Language Models with human values of helpfulness, honesty, and harmlessness. My work directly contributed to reducing model hallucinations and improving response accuracy for complex user queries.
In this role, I served as a Subject Matter Expert to align Large Language Models with human values of helpfulness, honesty, and harmlessness. My work directly contributed to reducing model hallucinations and improving response accuracy for complex user queries.
2023 - Present