Swedish LLM Evaluator

Participate in Project Spearmint, a multilingual AI response evaluation project focused on reviewing large language model (LLM) outputs in Swedish. Your role involves evaluating model replies in your native language based on either Tone or Fluency, assessing the overall quality, correctness, and naturalness of responses. You will read the user prompt and two model replies, then rate each using a five-point scale and provide brief rationales for any extreme ratings. Batches include evaluating whether replies are helpful, insightful, engaging, and fair, flagging formality mismatches, condescension, or bias, or assessing grammatical accuracy, clarity, coherence, and natural flow. This is a project-based opportunity to contribute from home.