---
title: Fine-Tuning Large Language Models for Financial Markets via Ontological Reasoning
url: https://www.ml-quant.com/papers/ssrn/5274196/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 5274196
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5274196
featured: 2025-05-30
citations: 1
topic: LLMs & Text
---


# Fine-Tuning Large Language Models for Financial Markets via Ontological Reasoning

Large Language Models struggle with accuracy in specialized fields due to lack of specific knowledge in training data, a problem that can be solved by fine-tuning with domain-specific data.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5274196
- Identifier: SSRN 5274196
- Released: 2025-05-29
- First featured: Quant Letter No. 99 (2025-05-30): https://www.ml-quant.com/issues/2025-05-30/
- Citations (Semantic Scholar): 1
- Published in: not yet
- Topic: LLMs & Text

## Related

- [Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?](https://www.ml-quant.com/papers/arxiv/2405.05904/): Research shows that large language models have difficulty acquiring new factual knowledge through fine-tuning, learning new information slower than consistent knowledge, and are more likely to hallucinate, indicating the risks of introducing new facts through fine-tuning.
- [TableLlama: Towards Open Large Generalist Models for Tables](https://www.ml-quant.com/papers/arxiv/2311.09206/): The paper presents TableLlama, an open-source large language model fine-tuned for table-based tasks, and introduces a new dataset, TableInstruct, which improves the performance and generalizability of these models.
- [Designing Heterogeneous LLM Agents for Financial Sentiment Analysis](https://www.ml-quant.com/papers/arxiv/2401.05799/): A study suggests using large language models without fine-tuning for financial sentiment analysis, offering a design framework that enhances accuracy.
- [Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models](https://www.ml-quant.com/papers/arxiv/2306.12659/): A new approach improves financial sentiment analysis by addressing limitations of language models.
- [AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation](https://www.ml-quant.com/papers/arxiv/2408.00764/): Enhancing LLM Planning: The study improves the planning abilities of Large Language Models (LLMs) using instruction tuning and a framework called AgentGen, which generates diverse environments and planning tasks.
- [RAG-IT: Retrieval-Augmented Instruction Tuning for Automated Financial Analysis - A Case Study for the Semiconductor Sector](https://www.ml-quant.com/papers/arxiv/2412.08179/): The study introduces a new method for automating earnings reports analysis using Large Language Models, with promising initial findings.