Paper: arXiv 2604.14793

Authors: Wei Wei, Jin Zheng, Zining Wang, Weibin Feng

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.

Complexity vs Empirical Score

  • Math Complexity: 2.5/10
  • Empirical Rigor: 6.0/10 (capped from 7.5: no out-of-sample test; see penalty flags)
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper focuses on the practical application of NLP and LLMs for large-scale systematic literature reviews rather than novel mathematical derivations. Its strength lies in the systematic evaluation of framework performance across a large corpus of 12,666 financial articles, demonstrating a highly pragmatic and implementation-oriented approach to financial research taxonomy.

Research Flowchart

  flowchart TD
    A[Research Goal: Automate/Scale Systematic Literature Reviews] --> B[Data Input: 12,666 Option Pricing Articles]
    B --> C[Methodology: LR-Robot Framework]
    C --> D[Processes: Taxonomy Definition, LLM Classification & Human-in-the-Loop Validation]
    D --> E[Analysis: RAG-based Temporal Tracking & Citation Networks]
    E --> F[Outcomes: Research Trends, Structural Patterns & Reliable Synthesis]

Cited References (77)

  1. Literature review as a research methodology: An overview and guidelines (2019)
  2. Analyzing the past to prepare for the future: Writing a literature review (2002)
  3. On being ‘systematic’in literature reviews in IS (2015)
  4. A typology of reviews: an analysis of 14 review types and associated methodologies (2009)
  5. How to conduct systematic reviews more expeditiously? (2015)
  6. A guide to conducting a standalone systematic literature review (2015)
  7. Clustering scientific publications based on citation relations: A systematic comparison of different methods (2016)
  8. A bibliometric analysis of global research output on network meta-analysis (2021)
and 69 more
  1. How to conduct a bibliometric analysis: An overview and guidelines (2021)
  2. A systematic review and bibliometric analysis of the dark side of customer behavior: An integrative customer incivility framework (2023)
  3. Do they agree? Bibliometric evaluation versus informed peer review in the Italian research assessment exercise (2016)
  4. Looking for landmarks: the role of expert review and bibliometric analysis in evaluating scientific publication outputs (2009)
  5. Artificial intelligence for literature reviews: Opportunities and challenges (2024)
  6. Automating systematic literature reviews with retrieval-augmented generation: a comprehensive overview (2024)
  7. Title and abstract screening for literature reviews using large language models: an exploratory study in the biomedical domain (2024)
  8. LitLLMs, LLMs for Literature Review: Are we there yet? (2024) — link
  9. Integrating conversational agents and knowledge graphs within the scholarly domain (2023)
  10. Cso classifier 3.0: a scalable unsupervised method for classifying documents in terms of research topics (2022)
  11. Non-parametric insights in option pricing: a systematic review of theory, implementation and future directions (2025) — link
  12. Neural networks for option pricing and hedging: a literature review (2020) — link
  13. Option Pricing: Valuation Models and Applications (2004) — link
  14. Centrality in social networks conceptual clarification (1978)
  15. The PageRank citation ranking: Bringing order to the web. (1999)
  16. A set of measures of centrality based on betweenness (1977)
  17. The pricing of options and corporate liabilities (1973)
  18. A closed-form solution for options with stochastic volatility with applications to bond and currency options (1993)
  19. Option pricing when underlying stock returns are discontinuous (1976)
  20. Option pricing: A simplified approach (1979) — link
  21. The pricing of options on assets with stochastic volatilities (1987)
  22. Valuing American options by simulation: A simple least-squares approach (2001)
  23. The valuation of options for alternative stochastic processes (1976)
  24. Empirical performance of alternative option pricing models (1997)
  25. A jump-diffusion model for option pricing (2002)
  26. Jumps and stochastic volatility: Exchange rate processes implicit in deutsche mark options (1996)
  27. Option valuation using the fast Fourier transform (1999)
  28. Martingales and arbitrage in multiperiod securities markets (1979)
  29. Martingales and stochastic integrals in the theory of continuous trading (1981)
  30. On the pricing of corporate debt: The risk structure of interest rates (1974)
  31. The finite moment log stable process and option pricing (2003)
  32. American option valuation: new bounds, approximations, and a comparison of existing methods (1996)
  33. Monte Carlo methods for security pricing (1997)
  34. A novel pricing method for European options based on Fourier-cosine series expansions (2009)
  35. A fast and accurate FFT-based method for pricing early-exercise options under L 'e vy processes (2008)
  36. Option pricing under a double exponential jump diffusion model (2004)
  37. Pricing early-exercise and discrete barrier options by Fourier-cosine series expansions (2009)
  38. The value of an option to exchange one asset for another (1978)
  39. Bond pricing and the term structure of interest rates: A new methodology for contingent claims valuation (1992)
  40. Implied binomial trees (1994)
  41. A nonparametric approach to pricing and hedging derivative securities via learning networks (1994)
  42. Option price forecasting using neural networks (2000)
  43. Regression methods for pricing complex American-style options (2001)
  44. Pricing and hedging derivative securities with neural networks and a homogeneity hint (2000)
  45. A neural network versus Black–Scholes: a comparison of pricing and hedging performances (2003)
  46. Riding on a smile (1994)
  47. Term structure movements and pricing interest rate contingent claims (1986)
  48. Variational inequalities and the pricing of American options (1990)
  49. The American put option valued analytically (1984)
  50. The analytic valuation of American options (1990)
  51. The value of an Asian option (1995)
  52. A continuity correction for discrete barrier options (1997)
  53. Bumping up against the barrier with the binomial method (1994)
  54. A closed-form GARCH option valuation model (2000)
  55. Nonparametric estimation of state-price densities implicit in financial asset prices (1998)
  56. Neural networks for option pricing and hedging: a literature review (2019) — link
  57. Empirical option pricing models (2022)
  58. Review of research on option pricing: A bibliometric analysis (2024)
  59. Latent dirichlet allocation (2003)
  60. BERTopic: Neural topic modeling with a class-based TF-IDF procedure (2022) — link
  61. Large-Scale Multidimensional Knowledge Profiling of Scientific Literature (2026) — link
  62. An open source machine learning framework for efficient and transparent systematic reviews (2021)
  63. Rayyan—a web and mobile app for systematic reviews (2016)
  64. Financebench: A new benchmark for financial question answering (2023) — link
  65. Open finllm leaderboard: Towards financial ai readiness (2025) — link
  66. XFinBench: Benchmarking LLMs in complex financial problem solving and reasoning (2025)
  67. The valuation of compound options (1979)
  68. Machine Reading Tea Leaves: Automatically Evaluating Topic Coherence and Topic Model Quality (2014) — link
  69. Topic Modeling in Embedding Spaces (2020) — link

0 of 77 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.