BASES: Large-scale Web Search User Simulation with Large Language Model based Agents

arXiv:2402.17505v1 Announce Type: cross
Abstract: Due to the excellent capacities of large language models (LLMs), it becomes feasible to develop LLM-based agents for reliable user simulation. Considering the scarcity and limit (e.g., privacy issues) of real user data, in this paper, we conduct large-scale user simulation for web search, to improve the analysis and modeling of user search behavior. Specially, we propose BASES, a novel user simulation framework with LLM-based agents, designed to facilitate comprehensive simulations of web search user …

abstract agents arxiv cs.cl cs.ir data language language model language models large language large language model large language models llm llms paper privacy scale search simulation type user data web web search