MIR: Methodology Inspiration Retrieval for Scientific Research Problems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913868673974272 |
|---|---|
| author | Garikaparthi, Aniketh Patwardhan, Manasi Kanade, Aditya Sanjiv Hassan, Aman Vig, Lovekesh Cohan, Arman |
| author_facet | Garikaparthi, Aniketh Patwardhan, Manasi Kanade, Aditya Sanjiv Hassan, Aman Vig, Lovekesh Cohan, Arman |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00249 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIR: Methodology Inspiration Retrieval for Scientific Research Problems Garikaparthi, Aniketh Patwardhan, Manasi Kanade, Aditya Sanjiv Hassan, Aman Vig, Lovekesh Cohan, Arman Artificial Intelligence Computation and Language 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. |
| title | MIR: Methodology Inspiration Retrieval for Scientific Research Problems |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2506.00249 |