GAPMAP: Mapping Scientific Knowledge Gaps in Biomedical Literature Using Large Language Models

TL;DR

This paper explores how large language models can identify explicit and implicit knowledge gaps in biomedical literature, demonstrating their potential to support research and policy decisions through structured reasoning schemes.

Contribution

It introduces a novel task of inferring implicit knowledge gaps and proposes the TABI reasoning scheme, benchmarking various LLMs on biomedical literature for gap detection.

Findings

LLMs can effectively identify both explicit and implicit knowledge gaps.

Larger models tend to perform better in gap detection tasks.

The TABI scheme improves reasoning and validation of inferred gaps.

Abstract

Scientific progress is driven by the deliberate articulation of what remains unknown. This study investigates the ability of large language models (LLMs) to identify research knowledge gaps in the biomedical literature. We define two categories of knowledge gaps: explicit gaps, clear declarations of missing knowledge; and implicit gaps, context-inferred missing knowledge. While prior work has focused mainly on explicit gap detection, we extend this line of research by addressing the novel task of inferring implicit gaps. We conducted two experiments on almost 1500 documents across four datasets, including a manually annotated corpus of biomedical articles. We benchmarked both closed-weight models (from OpenAI) and open-weight models (Llama and Gemma 2) under paragraph-level and full-paper settings. To address the reasoning of implicit gaps inference, we introduce \textbf{\small TABI}, a Toulmin-Abductive Bucketed Inference scheme that structures reasoning and buckets inferred conclusion candidates for validation. Our results highlight the robust capability of LLMs in identifying both explicit and implicit knowledge gaps. This is true for both open- and closed-weight models, with larger variants often performing better. This suggests a strong ability of LLMs for systematically identifying candidate knowledge gaps, which can support early-stage research formulation, policymakers, and funding decisions. We also report observed failure modes and outline directions for robust deployment, including domain adaptation, human-in-the-loop verification, and benchmarking across open- and closed-weight models.