@inproceedings{tatarinov-etal-2026-language,
title = "Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities",
author = "Tatarinov, Nikita and
Sukhani, Siddhant and
Shah, Agam and
Chava, Sudheer",
editor = "Mille, Simon and
Gehrmann, Sebastian and
Schmidtov{\'a}, Patr{\'i}cia and
Du{\v{s}}ek, Ond{\v{r}}ej and
Fadaee, Marzieh and
Lo, Kyle and
Santus, Enrico and
Stanovsky, Gabriel",
booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gem-main.65/",
pages = "718--744",
ISBN = "979-8-89176-423-1",
abstract = "Recent advances in language modeling have led to a growing number of papers related to finance in top-tier Natural Language Processing (NLP) venues. To systematically examine this trend, we review 374 NLP research papers published between 2017 and 2024 across 38 conferences and workshops, with a focused analysis of 221 papers that directly address finance-related tasks. We evaluate these papers across 11 quantitative and qualitative dimensions, with particular attention to evaluation practices, metric choices, dataset coverage, and reproducibility in a high-stakes applied LM domain. Our study identifies the following opportunities for NLP researchers: (i) expanding the scope of forecasting tasks; (ii) enriching evaluation with finance-specific metrics; (iii) leveraging multilingual and crisis-period datasets for robustness-oriented evaluation; and (iv) balancing PLMs with efficient or interpretable alternatives. We identify actionable directions supported by dataset and tool recommendations, with implications for both academic evaluation practices and industry deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tatarinov-etal-2026-language">
<titleInfo>
<title>Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Tatarinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddhant</namePart>
<namePart type="family">Sukhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agam</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudheer</namePart>
<namePart type="family">Chava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Fadaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-423-1</identifier>
</relatedItem>
<abstract>Recent advances in language modeling have led to a growing number of papers related to finance in top-tier Natural Language Processing (NLP) venues. To systematically examine this trend, we review 374 NLP research papers published between 2017 and 2024 across 38 conferences and workshops, with a focused analysis of 221 papers that directly address finance-related tasks. We evaluate these papers across 11 quantitative and qualitative dimensions, with particular attention to evaluation practices, metric choices, dataset coverage, and reproducibility in a high-stakes applied LM domain. Our study identifies the following opportunities for NLP researchers: (i) expanding the scope of forecasting tasks; (ii) enriching evaluation with finance-specific metrics; (iii) leveraging multilingual and crisis-period datasets for robustness-oriented evaluation; and (iv) balancing PLMs with efficient or interpretable alternatives. We identify actionable directions supported by dataset and tool recommendations, with implications for both academic evaluation practices and industry deployment.</abstract>
<identifier type="citekey">tatarinov-etal-2026-language</identifier>
<location>
<url>https://aclanthology.org/2026.gem-main.65/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>718</start>
<end>744</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities
%A Tatarinov, Nikita
%A Sukhani, Siddhant
%A Shah, Agam
%A Chava, Sudheer
%Y Mille, Simon
%Y Gehrmann, Sebastian
%Y Schmidtová, Patrícia
%Y Dušek, Ondřej
%Y Fadaee, Marzieh
%Y Lo, Kyle
%Y Santus, Enrico
%Y Stanovsky, Gabriel
%S Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-423-1
%F tatarinov-etal-2026-language
%X Recent advances in language modeling have led to a growing number of papers related to finance in top-tier Natural Language Processing (NLP) venues. To systematically examine this trend, we review 374 NLP research papers published between 2017 and 2024 across 38 conferences and workshops, with a focused analysis of 221 papers that directly address finance-related tasks. We evaluate these papers across 11 quantitative and qualitative dimensions, with particular attention to evaluation practices, metric choices, dataset coverage, and reproducibility in a high-stakes applied LM domain. Our study identifies the following opportunities for NLP researchers: (i) expanding the scope of forecasting tasks; (ii) enriching evaluation with finance-specific metrics; (iii) leveraging multilingual and crisis-period datasets for robustness-oriented evaluation; and (iv) balancing PLMs with efficient or interpretable alternatives. We identify actionable directions supported by dataset and tool recommendations, with implications for both academic evaluation practices and industry deployment.
%U https://aclanthology.org/2026.gem-main.65/
%P 718-744
Markdown (Informal)
[Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities](https://aclanthology.org/2026.gem-main.65/) (Tatarinov et al., GEM 2026)
ACL
- Nikita Tatarinov, Siddhant Sukhani, Agam Shah, and Sudheer Chava. 2026. Language Modeling for the Future of Finance: A Survey into Metrics, Tasks, and Data Opportunities. In Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM), pages 718–744, San Diego, California, USA. Association for Computational Linguistics.