Scideator: Human-LLM Scientific Idea Generation Grounded in Research-Paper Facet Recombination
The scientific ideation process often involves blending salient aspects of existing papers to create new ideas, and facet-based ideation is an established framework for idea generation. To see how large language models (LLMs) might assist in this process, we contribute a novel mixed-initiative ideation tool called Scideator. Starting from a user-provided set of scientific papers, Scideator extracts key facets -- purposes, mechanisms, and evaluations -- from these and related papers, allowing users to explore the idea space by interactively recombining facets to synthesize inventive ideas. Scideator also helps users gauge idea originality by searching the literature for overlaps, assessing idea novelty and providing explanations. To support these tasks, Scideator introduces three LLM-powered retrieval-augmented generation (RAG) modules: Analogous Paper Facet Finder, Faceted Idea Generator, and Idea Novelty Checker. In a within-subjects user study (N=22) with computer-science researchers comparing Scideator to a strong baseline, our tool provided significantly more creativity support, particularly with respect to exploration, which participants considered the most important factor for idea generation.
Code (0)
등록된 구현이 없습니다.
Tasks
RAGRetrieval-augmented GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models
Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research workflows, yet inadequately model scientific reasoning, resulting in sur…
Reinforcement LearningHypER: Literature-grounded Hypothesis Generation and Distillation with Provenance
Large Language models have demonstrated promising performance in research ideation across scientific domains. Hypothesis development, the process of generating a highly specific declarative statement connecting a researc…
Language ModelingLanguage ModellingSmall Language ModelvalidIdeas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks still say little about whether AI…
Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models
Large language models (LLMs) have demonstrated remarkable capabilities in various scientific domains, from natural language processing to complex problem-solving tasks. Their ability to understand and generate human-like…
Experimental DesignHallucinationKnowledge GraphsGrounded Intuition of GPT-Vision's Abilities with Scientific Images
GPT-Vision has impressed us on a range of vision-language tasks, but it comes with the familiar new challenge: we have little idea of its capabilities and limitations. In our study, we formalize a process that many have …
BenchmarkingcounterfactualText Generation