LR-Robot: An Human-in-the-Loop LLM Framework for Systematic Literature Reviews with Applications in Financial Research

2026-04-16

AI Summary

This study addresses the inefficiency of traditional systematic literature reviews in finance, exacerbated by the exponential growth of scholarly output. To overcome this challenge, the authors propose a human–AI collaborative framework in which domain experts construct a multidimensional taxonomy and design prompt constraints to guide large language models (LLMs) in performing interpretable, customizable classification of massive literature corpora. Human-in-the-loop feedback and retrieval-augmented generation (RAG) are integrated to ensure analytical reliability and depth. Empirical evaluation on a dataset of 12,666 papers on option pricing demonstrates that the approach substantially enhances both the efficiency and accuracy of literature synthesis. The work achieves the first effective integration of expert-guided multidimensional categorization with scalable LLM processing and provides a systematic benchmark of 11 leading LLMs, uncovering key research trends and structural patterns in the field.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Crowd Sourcing and Human Computation
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The exponential growth of financial research has rendered traditional systematic literature reviews (SLRs) increasingly impractical, as manual screening and narrative synthesis struggle to keep pace with the scale and complexity of modern scholarship. While the existing artificial intelligence (AI) and natural language processing (NLP) approaches often often produce outputs that are efficient but contextually limited, still requiring substantial expert oversight. To address these challenges, we propose LR-Robot, a novel framework in which domain experts define multidimensional classification taxonomies and prompt constraints that encode conceptual boundaries, large language models (LLMs) execute scalable classification across large corpora, and systematic human-in-the-loop evaluation ensures reliability before full-dataset deployment.The framework further leverages retrieval-augmented generation (RAG) to support downstream analyses including temporal evolution tracking and label-enhanced citation networks. We demonstrate the framework on a corpus of 12,666 option pricing articles spanning 50 years, designing a four-dimensional taxonomy and systematically evaluating up to eleven mainstream LLMs across classification tasks of varying complexity. The results reveal the current capabilities of AI in understanding and synthesizing literature, uncover emerging trends, reveal structural research patterns, and highlight core research directions. By accelerating labor-intensive review stages while preserving interpretive accuracy, LR-Robot provides a practical, customizable, and high-quality approach for AI-assisted SLRs.

Problem

• systematic literature reviews
• financial research
• large language models
• human-in-the-loop
• natural language processing

Innovation

• Human-in-the-Loop
• Large Language Models
• Systematic Literature Review
• Retrieval-Augmented Generation
• Multidimensional Taxonomy