Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation

TL;DR

Scideator is a human-LLM system that facilitates scientific ideation by extracting, recombining, and evaluating facets of existing papers to generate novel ideas through an interactive, facet-based approach.

Contribution

This work introduces the first human-LLM system for facet-based scientific ideation, integrating human-in-the-loop recombination, spectrum-based retrieval, and facet-driven novelty evaluation.

Findings

Scideator significantly enhances creativity support over baseline systems.

Facet-based retrieval improves relevance of related papers.

Facet-grounded novelty classifier outperforms unstructured approaches.

Abstract

The scientific ideation process often involves blending facets of existing papers to create new ideas. We contribute Scideator, the first human-LLM system for facet-based scientific ideation. Starting from user-provided papers, Scideator extracts key facets -- purposes, mechanisms, and evaluations -- from these and related papers, allowing users to interactively recombine facets to synthesize ideas. Scideator is driven by three design choices: (1) human-in-the-loop facet recombination, in which users select facets from retrieved papers and the system generates ideas by finding analogies across them via the Faceted Idea Generator module; (2) distance-controlled retrieval via the Analogous Paper Facet Finder module, which surfaces papers ranging from the same topic to entirely different areas to provide a spectrum of directions; and (3) facet-based novelty verification via the Idea Novelty Checker module, a retrieve-then-rerank pipeline that helps users to evaluate idea originality using facets. In a user study with computer science researchers, Scideator provided significantly more creativity support than a baseline using the same backbone LLM without our facet-based modules, particularly in idea exploration and expressiveness. Ablations further show that the facets benefit the novelty checker: facet-based retrieve-then-rerank surfaces more relevant papers than standard retrieval and re-ranking, and a facet-grounded novelty classifier outperforms classifiers that reason over unstructured ideas and papers.