Search papers, labs, and topics across Lattice.
The paper introduces Agent4DL, a user search behavior simulator leveraging LLMs to generate realistic user profiles and search sessions within digital library environments, addressing the lack of real-world user data due to privacy. Agent4DL simulates querying, clicking, and stopping behaviors tailored to user profiles and validated against real user data. Agent4DL demonstrates competitive performance against SimIIR 2.0, generating more diverse and context-aware user behaviors.
Forget relying on scarce, privacy-hampered real user data – Agent4DL lets you simulate realistic digital library search behavior with LLMs, outperforming existing simulators in diversity and context-awareness.
In the rapidly evolving field of digital libraries, the development of large language models (LLMs) has opened up new possibilities for simulating user behavior. This innovation addresses the longstanding challenge in digital library research: the scarcity of publicly available datasets on user search patterns due to privacy concerns. In this context, we introduce Agent4DL, a user search behavior simulator specifically designed for digital library environments. Agent4DL generates realistic user profiles and dynamic search sessions that closely mimic actual search strategies, including querying, clicking, and stopping behaviors tailored to specific user profiles. Our simulator's accuracy in replicating real user interactions has been validated through comparisons with real user data. Notably, Agent4DL demonstrates competitive performance compared to existing user search simulators such as SimIIR 2.0, particularly in its ability to generate more diverse and context-aware user behaviors.
