Truace
Subscribe

From General-Purpose Large Language Models to Domain-Specific Financial Models: A Structured Review and Comparative Case Analysis

The use of large language models (LLMs) in finance has expanded rapidly, yet general-purpose systems face recurring problems in high-risk and regulated applications: Unsupported factual generation, weak reasoning across text, tables, charts, and numerical data, and limited traceability of model-assisted decisions. This study conducts a Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA)-informed structured review of 67 studies, principally published between January 2020 and March 2026, wi…

By the Truvace desk2 min read1 sourcePeer-reviewedTRV-2026-1419· cite & verify
From General-Purpose Large Language Models to Domain-Specific Financial Models: A Structured Review and Comparative Case Analysis
Large Scale Shrub Biomass Estimates for Multiple Purposes by Teresa Enes, José Lousada, Teresa Fonseca, Hélder Viana, Ana Calvão, and José Aranha. CC BY 4.0 · https://creativecommons.org/licenses/by/4.0

In brief

The use of large language models (LLMs) in finance has expanded rapidly, yet general-purpose systems face recurring problems in high-risk and regulated applications: Unsupported factual generation, weak reasoning across text, tables, charts, and numerical data, and limited traceability of model-assisted decisions. This study conducts a Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA)-informed structured review of 67 studies, principally published between January 2020 and March 2026, with three foundational pre-2020 studies retained through backward citation tracking.

The analysis indicates that financial LLMs differ materially in how they organize domain knowledge, coordinate heterogeneous inputs, and govern model use across the lifecycle. The paper provides a structured basis for assessing domain-specific financial LLMs and connects responsible model design with sustainable financial innovation through durable governance arrangements, controlled model and compliance risk, responsible scaling, financial inclusion, and institutional resilience.

Main points

  1. This study conducts a Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA)-informed structured review of 67 studies, principally published between January 2020 and March 2026, with three foundational pre-2020 studies retained through backward citation tracking.
  2. It develops a qualitative analytical and diagnostic framework with three pathways: Specialized knowledge modeling, task-constrained multimodal reasoning, and Trust-by-Design.
  3. A study-level evidence map and an explicit coding protocol show how the pathways were derived.

The problem

The use of large language models (LLMs) in finance has expanded rapidly, yet general-purpose systems face recurring problems in high-risk and regulated applications: Unsupported factual generation, weak reasoning across text, tables, charts, and numerical data, and limited traceability of model-assisted decisions.

The rundown

It develops a qualitative analytical and diagnostic framework with three pathways: Specialized knowledge modeling, task-constrained multimodal reasoning, and Trust-by-Design. A study-level evidence map and an explicit coding protocol show how the pathways were derived.

Sources

  1. Peer-reviewedFinTech and Sustainable Innovation2026-10-14

The debate