Eunice Kim

Key Skills

Software

Mercor

Top Subject Matter

LLM Training & Evaluation

Top Data Types

Text

Audio

Top Task Types

RLHF

Freelancer Overview

RLHF Korean Annotator (LLM Training & Evaluation). Brings 34+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Mercor and Prolific Research. Education includes Master of Religious Education, Southern Baptist Theological Seminary (1996) and Bachelor of Arts, San Francisco State University (1989). AI-training focus includes data types such as Text and labeling workflows including RLHF, Evaluation, and Rating.

Labeling Experience

RLHF Korean Annotator (LLM Training & Evaluation)

MercorTextRLHF

As an RLHF Korean Annotator at Mercor, I specialize in evaluating and refining AI-generated Korean–English responses using RLHF methodologies. My core focus includes assessing factual accuracy, linguistic quality, and cultural nuance using strict guidelines and rubrics. I consistently deliver high-quality evaluations that improve large language model (LLM) outputs. • Reviewed and ranked bilingual AI-generated text for accuracy, fluency, and contextual appropriateness • Identified translation errors and unnatural phrasing in model outputs • Followed detailed RLHF guidelines and quality standards • Collaborated to enhance language model alignment and reliability

As an RLHF Korean Annotator at Mercor, I specialize in evaluating and refining AI-generated Korean–English responses using RLHF methodologies. My core focus includes assessing factual accuracy, linguistic quality, and cultural nuance using strict guidelines and rubrics. I consistently deliver high-quality evaluations that improve large language model (LLM) outputs. • Reviewed and ranked bilingual AI-generated text for accuracy, fluency, and contextual appropriateness • Identified translation errors and unnatural phrasing in model outputs • Followed detailed RLHF guidelines and quality standards • Collaborated to enhance language model alignment and reliability

2026 - Present

AI Response Evaluation & Fact-Checking (LLM Training)

TextEvaluation Rating

In my AI Response Evaluation & Fact-Checking role at Prolific Research, I evaluate AI-generated textual responses for accuracy, consistency, and relevance. My work helps safeguard against hallucinations and improves language model safety and reliability. I regularly apply structured, rubric-based quality checks to ensure best practices. • Flagged factual, logical, and linguistic errors in text outputs • Applied evaluation rubrics for detailed response assessments • Improved safety and reliability of LLM outputs • Identified cultural misinterpretations and ambiguous text

In my AI Response Evaluation & Fact-Checking role at Prolific Research, I evaluate AI-generated textual responses for accuracy, consistency, and relevance. My work helps safeguard against hallucinations and improves language model safety and reliability. I regularly apply structured, rubric-based quality checks to ensure best practices. • Flagged factual, logical, and linguistic errors in text outputs • Applied evaluation rubrics for detailed response assessments • Improved safety and reliability of LLM outputs • Identified cultural misinterpretations and ambiguous text

2024 - Present

Education

Work History