4 papers · 2 filters
ZERA: Zero-init Instruction Evolving Refinement Agent -- From Zero Instructions to Structured Prompts via Principle-based Optimization
Seungyoun Yi, Minsoo Khang, Sungrae Park
Automatic Prompt Optimization (APO) improves large language model (LLM) performance by refining prompts for specific tasks. However, prior APO methods typically focus only on user…
CReSt: A Comprehensive Benchmark for Retrieval-Augmented Generation with Complex Reasoning over Structured Documents
Minsoo Khang, Sangjun Park, Teakgyu Hong +1
Large Language Models (LLMs) have made substantial progress in recent years, yet evaluating their capabilities in practical Retrieval-Augmented Generation (RAG) scenarios remains c…
KIEval: Evaluation Metric for Document Key Information Extraction
Minsoo Khang, Sang Chul Jung, Sungrae Park +1
Document Key Information Extraction (KIE) is a technology that transforms valuable information in document images into structured data, and it has become an essential function in i…
System Message Generation for User Preferences using Open-Source Models
Minbyul Jeong, Jungho Cho, Minsoo Khang +2
System messages play a crucial role in interactions with large language models (LLMs), often serving as prompts to initiate conversations. Through system messages, users can assign…