LLM Evaluation and Data Annotation (Self-directed/Academic)
Text
Evaluated and rated AI-generated responses across a range of domains using structured criteria. Fact-checked information, assessed response accuracy and clarity, and provided constructive, high-quality feedback. Performed comparative analysis of multiple LLM outputs to select the most accurate and relevant. Applied consistent standards for accuracy, relevance, and usefulness in all assessments.
• Strong focus on identifying reasoning errors, factual inaccuracies, and clarity issues.
• Structured feedback on clarity, tone, and completeness.
• Highly detail-oriented approach to error detection and quality assessment.
• Engaged with LLM model outputs in both Arabic and English contexts.
Evaluated and rated AI-generated responses across a range of domains using structured criteria. Fact-checked information, assessed response accuracy and clarity, and provided constructive, high-quality feedback. Performed comparative analysis of multiple LLM outputs to select the most accurate and relevant. Applied consistent standards for accuracy, relevance, and usefulness in all assessments. • Strong focus on identifying reasoning errors, factual inaccuracies, and clarity issues. • Structured feedback on clarity, tone, and completeness. • Highly detail-oriented approach to error detection and quality assessment. • Engaged with LLM model outputs in both Arabic and English contexts.
2024 - Present