Search papers, labs, and topics across Lattice.
Sci-Surf is an intent-centric knowledge discovery system designed to enhance the navigation of scientific literature by integrating feedback-driven personalized recommendations with multi-modal summarization of research papers. By leveraging LLM-based user profiling, the system refines user intent representations and generates structured summaries that combine textual and visual information from full papers. The results indicate a significant 10.4% improvement in predictive alignment with user preferences, showcasing the system's effectiveness in improving both recommendation and digestion quality.
Personalized feedback-driven recommendations can boost literature discovery effectiveness by over 10% in aligning with user preferences.
The rapid growth of scientific publications makes it increasingly difficult for researchers to identify relevant new studies and effectively comprehend them. Existing academic discovery platforms typically rely on static topic subscriptions or embedding-based similarity and provide only abstracts or short summaries, offering limited support for nuanced intent modeling and in-depth paper summarization. We present Sci-Surf, an intent-centric knowledge discovery system that integrates feedback-driven personalized recommendation with multi-modal blog-style paper digestion. Our approach refines user intent representations through LLM-based user profiling, while generating structured summaries that synthesize textual and visual information from full papers. The demo presents an end-to-end academic discovery pipeline and demonstrates measurable improvements in both recommendation quality and digestion quality through real-user evaluations. Specifically, the integration of verbalized profiles led to a 10.4% average improvement in predictive alignment with real-world user preferences throughout a month-long online evaluation.
