IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback
arXiv:2410.04025 · doi:10.1145/3706598.3714057
Abstract
Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support for iterative specification, refinement, and evaluation needed to further develop initial ideas. To bridge this gap, we introduce IdeaSynth, a research idea development system that uses LLMs to provide literature-grounded feedback for articulating research problems, solutions, evaluations, and contributions. IdeaSynth represents these idea facets as nodes on a canvas, and allow researchers to iteratively refine them by creating and exploring variations and composing them. Our lab study (N=20) showed that participants, while using IdeaSynth, explored more alternative ideas and expanded initial ideas with more details compared to a strong LLM-based baseline. Our deployment study (N=7) demonstrated that participants effectively used IdeaSynth for real-world research projects at various ideation stages from developing initial ideas to revising framings of mature manuscripts, highlighting the possibilities to adopt IdeaSynth in researcher's workflows.
References in corpus (9)
- To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making
- The Effects of Generative AI on Design Fixation and Divergent Thinking
- Homogenization Effects of Large Language Models on Human Creative Ideation
- Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era
- Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemaking
- PaperRobot: Incremental Draft Generation of Scientific Ideas
- ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models
- Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders
- MARG: Multi-Agent Review Generation for Scientific Papers