Saved in:
Bibliographic Details
Main Authors: Matlin, Glenn, Okamoto, Mika, Pardawala, Huzaifa, Yang, Yang, Chava, Sudheer
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.15846
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912439685087232
author Matlin, Glenn
Okamoto, Mika
Pardawala, Huzaifa
Yang, Yang
Chava, Sudheer
author_facet Matlin, Glenn
Okamoto, Mika
Pardawala, Huzaifa
Yang, Yang
Chava, Sudheer
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15846
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Finance Language Model Evaluation (FLaME)
Matlin, Glenn
Okamoto, Mika
Pardawala, Huzaifa
Yang, Yang
Chava, Sudheer
Computation and Language
Artificial Intelligence
Computational Engineering, Finance, and Science
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.
title Finance Language Model Evaluation (FLaME)
topic Computation and Language
Artificial Intelligence
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2506.15846