Papers › Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models

Exploring the Impact of Corpus Diversity on Financial Pretrained Language Models

20 Oct 2023arXiv:2310.13312archive 2025-07-28

Jaeyoung Choe, Keonwoong Noh, Nayeon Kim, Seyun Ahn, Woohwan Jung

Over the past few years, various domain-specific pretrained language models (PLMs) have been proposed and have outperformed general-domain PLMs in specialized areas such as biomedical, scientific, and clinical domains. In addition, financial PLMs have been studied because of the high economic impact of financial data analysis. However, we found that financial PLMs were not pretrained on sufficiently diverse financial data. This lack of diverse training data leads to a subpar generalization performance, resulting in general-purpose PLMs, including BERT, often outperforming financial PLMs on many downstream tasks. To address this issue, we collected a broad range of financial corpus and trained the Financial Language Model (FiLM) on these diverse datasets. Our experimental results confirm that FiLM outperforms not only existing financial PLMs but also general domain PLMs. Furthermore, we provide empirical evidence that this improvement can be achieved even for unseen corpus groups.

Paper PDF Code

Code

deep-over/film officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Diversity Language Modeling Language Modelling Sentiment Analysis

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Sentiment Analysis	Financial PhraseBank	FiLM	Accuracy	86.25	#1 of 2	Archive leaderboard	report
Sentiment Analysis	Financial PhraseBank	FiLM	F1 score	84.48	#1 of 2	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adam Attention Attention Dropout BERT Dense Connections Dropout Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections