MIR: Methodology Inspiration Retrieval for Scientific Research Problems
This addresses the problem of improving literature retrieval for scientific discovery by researchers, but it is incremental as it builds on existing retrieval methods with specific enhancements.
The paper tackles the challenge of retrieving prior scientific work that can inspire solutions for a given research problem, defined as Methodology Inspiration Retrieval (MIR), by building a Methodology Adjacency Graph to embed methodological lineage into dense retrievers, achieving gains of +5.4 in Recall@3 and +7.8 in mAP over baselines.
There has been a surge of interest in harnessing the reasoning capabilities of Large Language Models (LLMs) to accelerate scientific discovery. While existing approaches rely on grounding the discovery process within the relevant literature, effectiveness varies significantly with the quality and nature of the retrieved literature. We address the challenge of retrieving prior work whose concepts can inspire solutions for a given research problem, a task we define as Methodology Inspiration Retrieval (MIR). We construct a novel dataset tailored for training and evaluating retrievers on MIR, and establish baselines. To address MIR, we build the Methodology Adjacency Graph (MAG); capturing methodological lineage through citation relationships. We leverage MAG to embed an "intuitive prior" into dense retrievers for identifying patterns of methodological inspiration beyond superficial semantic similarity. This achieves significant gains of +5.4 in Recall@3 and +7.8 in Mean Average Precision (mAP) over strong baselines. Further, we adapt LLM-based re-ranking strategies to MIR, yielding additional improvements of +4.5 in Recall@3 and +4.8 in mAP. Through extensive ablation studies and qualitative analyses, we exhibit the promise of MIR in enhancing automated scientific discovery and outline avenues for advancing inspiration-driven retrieval.