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

TL;DR

BASES addresses the scarcity and privacy concerns of real user data by using LLM-based agents to simulate large-scale web search user behavior. It introduces a synergistic synthesis approach to construct diverse user profiles and two targeted prompting strategies to generate query and click actions. The framework is validated on two IR tasks in Chinese and English, showing improvements over baselines and strong performance in low-resource settings; it also yields the WARRIORS dataset of 100k simulated sessions. These results demonstrate the feasibility and value of privacy-preserving user simulation for advancing information retrieval research.

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 behaviors. Our simulation framework can generate unique user profiles at scale, which subsequently leads to diverse search behaviors. To demonstrate the effectiveness of BASES, we conduct evaluation experiments based on two human benchmarks in both Chinese and English, demonstrating that BASES can effectively simulate large-scale human-like search behaviors. To further accommodate the research on web search, we develop WARRIORS, a new large-scale dataset encompassing web search user behaviors, including both Chinese and English versions, which can greatly bolster research in the field of information retrieval. Our code and data will be publicly released soon.

Figures (1)

• Figure 1: The profile structure for web search user simulation with a user sample.