Finance Language Model Evaluation (FLaME)
This work addresses the need for better evaluation methods in finance NLP, which is crucial for researchers and practitioners in the financial domain, though it is incremental as it builds on existing LM evaluation concepts.
The paper tackles the problem of evaluating language models for specialized finance tasks by introducing FLaME, a holistic benchmarking suite, and finds that existing frameworks underestimate LMs' performance, demonstrating their potential with an empirical study of 23 models over 20 finance NLP tasks.
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.