Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation
Songyang Gao, Yinghui Xia, Siyi Liu, Hui Xiong

TL;DR
This paper introduces Graphs of Research (GoR), a supervised fine-tuning method that leverages citation evolution graphs to improve research idea generation with large language models, achieving state-of-the-art results.
Contribution
The paper presents a novel approach using citation evolution graphs as supervision for fine-tuning LLMs to generate research ideas more effectively.
Findings
GoR-SFT outperforms GPT-4o-driven baselines in idea generation tasks.
Constructed a large dataset from major ML/NLP venues with citation graphs.
Fine-tuning on structured citation data improves research idea quality.
Abstract
Research idea generation is the innovation-driving step of automated scientific research. Recently, large language models (LLMs) have shown potential for automating idea generation at scale. However, existing methods mainly condition LLMs on eliciting idea generation through static retrieval of relevant literature or complex prompt engineering, without discarding the structural relations among references. We propose Graphs of Research (GoR), a supervised fine-tuning method that extracts a 2-hop reference neighborhood for each seed paper, derives the relations among those references from citation position, frequency, predecessor links, and publication time, and organizes them into a paper-evolution directed acyclic graph (DAG). We construct an automated extraction pipeline that draws data from five major ML/NLP venues, comprising 498/50/50 train/validation/test seed papers and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
