7 papers
SCOPE: Cost-Efficient Model Selection for Compound AI Systems under Quality Constraints
Yiqian Huang, Shiqi Zhang, Tianyuan Jin +1
A compound AI system consists of multiple LLM modules, together handling complex and multi-step tasks that exceed the capabilities of a single model. Existing systems often use a s…
NBQ: Next-Best-Question for Dynamic Profiling
Yimin Shi, Clarice Wang, Haixun Wang +1
Many real-world conversational settings for knowledge discovery, including podcasts, hiring screens, and marketplaces, require a purpose-driven understanding of a person. We study…
GEM-Bench: A Benchmark for Ad-Injected Response Generation within Generative Engine Marketing
Silan Hu, Shiqi Zhang, Yimin Shi +1
Generative Engine Marketing (GEM) is an emerging ecosystem for monetizing generative engines, such as LLM-based chatbots, by seamlessly integrating relevant advertisements into the…
ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries
Keke Huang, Yimin Shi, Dujian Ding +4
In recent years, large language models (LLMs) have demonstrated remarkable capabilities in comprehending and generating natural language content, attracting widespread attention in…
KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG
Yiqian Huang, Shiqi Zhang, Xiaokui Xiao
Graph-RAG constructs a knowledge graph from text chunks to improve retrieval in Large Language Model (LLM)-based question answering. It is particularly useful in domains such as bi…
You Are What You Bought: Generating Customer Personas for E-commerce Applications
Yimin Shi, Yang Fei, Shiqi Zhang +2
In e-commerce, user representations are essential for various applications. Existing methods often use deep learning techniques to convert customer behaviors into implicit embeddin…