Financial Narrative Processing 2025

FNP2025 will be part of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal).

The joint workshop explores the interaction of NLP, Machine Learning (ML), and Large Language Models (LLMs) within the financial and legal domains. By merging the expertise and focus areas of these three workshops, we intend to foster interdisciplinary research and innovation.

Since our first project in 2012, we have built a long and rich history in Financial NLP. Our 10th event marks the 6th under the title of FNP, highlighting the growing interest in automatic and computer-aided approaches for extracting, summarising, and analysing both qualitative and quantitative financial data. In recent years, previous manual small-scale research in the Accounting and Finance literature has been scaled up with the aid of NLP and ML methods. For the past five years, we have proven to be the leaders in Financial NLP, organising more than nine international events, introducing NLP and AI shared tasks, and providing the datasets and methodologies needed to push forward this emerging field.

Following the success of the 5th Financial Narrative Processing Workshop (FNP 2023) at the IEEE-BigData Conference in Sorrento, Italy, the 4th Financial Narrative Processing Workshop (FNP 2022) at LREC’22 in Marseille, the 3rd Financial Narrative Processing Workshop (FNP 2021), the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (FNP-FNS 2020), as well as the First FNP 2018 at LREC’18 in Japan, the Second FNP 2019 at NoDaLiDa 2019 in Finland and the Multiling 2019 Financial narrative Summarisation task at RANLP in Bulgaria, we have had a great deal of positive feedback and interest in continuing the development of the financial narrative processing field, especially from our shared task participants. Our workshop series are contributing to the field of Financial NLP, evident by Google Citations and proceedings on ACL anthology

As in previous editions, FNP 2025 will be on-site and in-person (there will be NO option for it to be virtual or hybrid).

For the 6th FNP shared task, we will continue working in two languages (English, Spanish) and we will introduce a new FinCausal Shared Task: Financial Causality Detection (FinCausal 2025) on hybrid question answering.

The objective is to detect causal effects in financial disclosures in English and Spanish. The dataset is a combination of extractive and generative QA. Questions will be formulated abstractedly, while answers will be extractive. In certain segments, questions will either focus on causes or effects, and the answers will be directly extracted from the text. The evaluation metric for responses will encompass both exact matching and semantic similarity.

The shared tasks attracted more than 150 participants within the last 3 FNP editions, for this year we are expanding the dataset by making the tasks more challenging.

→ 2 new datasets will be developed, one in English and one in Spanish