REVIEW 2 cited by
FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language models (LLMs) usually rely on extensive training datasets. In the financial domain, creating numerical reasoning datasets that include a mix of tables and long text often involves substantial manual annotation expenses. To address the limited data resources and reduce the annotation cost, we introduce FinLLMs, a method for generating financial question-answering data based on common financial formulas using Large Language Models. First, we compile a list of common financial formulas and construct a graph based on the variables these formulas employ. We then augment the formula set by combining those that share identical variables as new elements. Specifically, we explore formulas obtained by manual annotation and merge those formulas with shared variables by traversing the constructed graph. Finally, utilizing GPT-3.5, we generate financial question-answering data that encompasses both tabular information and long textual content, building on the collected formula set. Our experiments demonstrate that synthetic data generated by FinLLMs effectively enhances the performance of several large-scale numerical reasoning models in the financial domain, outperforming two established benchmark financial question-answering datasets.
Forward citations
Cited by 2 Pith papers
-
Reinforcement Fine-Tuning for Reasoning towards Multi-Step Multi-Source Search in Large Language Models
R-Search trains one LLM to reason, plan a multi-source search graph, and synthesize answers in a single pass, beating several search-augmented baselines.
-
CF-RAG: A Dataset and Method for Carbon Footprint QA Using Retrieval-Augmented Generation
A fine-tuned Llama 3 model with a trained document critic and program-based reasoning beats GPT-4o and other baselines on a new carbon footprint QA benchmark.
Discussion (0). Sign in to comment.