InFerActive: Towards Scalable Human Evaluation of Large Language Models through Interactive Inference

📝 Original Info

• Title: InFerActive: Towards Scalable Human Evaluation of Large Language Models through Interactive Inference
• ArXiv ID: 2512.10234
• Date: 2025-12-11
• Authors: Junhyeong Hwangbo, Soohyun Lee, Minsoo Cheong, Hyeon Jeon, Jinwook Seo

📝 Abstract

Human evaluation remains the gold standard for evaluating outputs of Large Language Models (LLMs). The current evaluation paradigm reviews numerous individual responses, leading to significant scalability challenges. LLM outputs can be more efficiently represented as a tree structure, reflecting their autoregressive generation process and stochastic token selection. However, conventional tree visualization cannot scale to the exponentially large trees generated by modern sampling methods of LLMs. To address this problem, we present InFerActive, an interactive inference system for

📄 Full Content

...(본문 내용이 길어 생략되었습니다. 사이트에서 전문을 확인해 주세요.)