MIR: Methodology Inspiration Retrieval for Scientific Research Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Garikaparthi, Aniketh, Patwardhan, Manasi, Kanade, Aditya Sanjiv, Hassan, Aman, Vig, Lovekesh, Cohan, Arman
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