Finance Language Model Evaluation (FLaME)

TL;DR

This paper introduces FLaME, a comprehensive benchmarking suite for evaluating financial language models, addressing gaps in existing frameworks and demonstrating the potential of LMs in finance through extensive empirical analysis.

Contribution

It presents the first holistic evaluation framework for FinNLP, including a comparative study of 23 foundation LMs on 20 finance-specific NLP tasks.

Findings

LMs show promising performance on finance NLP tasks

Reasoning-reinforced LMs outperform standard models

Open-source framework enables reproducibility and further research

Abstract

Language Models (LMs) have demonstrated impressive capabilities with core Natural Language Processing (NLP) tasks. The effectiveness of LMs for highly specialized knowledge-intensive tasks in finance remains difficult to assess due to major gaps in the methodologies of existing evaluation frameworks, which have caused an erroneous belief in a far lower bound of LMs' performance on common Finance NLP (FinNLP) tasks. To demonstrate the potential of LMs for these FinNLP tasks, we present the first holistic benchmarking suite for Financial Language Model Evaluation (FLaME). We are the first research paper to comprehensively study LMs against 'reasoning-reinforced' LMs, with an empirical study of 23 foundation LMs over 20 core NLP tasks in finance. We open-source our framework software along with all data and results.