#FinNLP
This afternoon, I'm attending 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) #COLING2025 sites.google.com/nlg.csie.ntu...
FinNLP-FNP-LLMFinLegal @ COLING-2025
Join Maillist for updating: https://forms.gle/wM8o5yVvRRbq2Q1c9 Introduction The joint workshop of FinNLP, FNP, and LLMFinLegal aims to explore the intersection of Natural Language Processing (NLP), ...
sites.google.com
January 19, 2025 at 10:52 AM
FinNLP-AgentScen@IJCAI-2024 Financial Challenges in Large Language Models - FinLLM sites.google.com/nlg.csie.ntu...
FinNLP-AgentScen @ IJCAI-2024 - Shared Task - FinLLM
Introduction With the advent of LLM in finance, financial text analysis, generation, and decision-making tasks have received growing attention, including financial classification, financial text summa...
sites.google.com
May 2, 2024 at 6:11 AM
W10: 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) (sites.google.com/nlg.csie.ntu...)
FinNLP-FNP-LLMFinLegal @ COLING-2025
Join Maillist for updating: https://forms.gle/wM8o5yVvRRbq2Q1c9 Introduction The joint workshop of FinNLP, FNP, and LLMFinLegal aims to explore the intersection of Natural Language Processing (NLP), ...
sites.google.com
January 18, 2025 at 3:40 PM
February 14, 2026 at 4:53 AM
Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide variety of Financial Natural Language Processing (FinNLP) tasks. However, systematic comparisons among widely used LLMs remain underexplored. Given the rapid advancement and growing influence of LLMs in financial analysis, this study conducts a thorough comparative evaluation of five leading LLMs, GPT, Claude, Perplexity, Gemini and DeepSeek, using 10-K filings from the 'Magnificent Seven' technology companies. We create a set of domain-specific prompts and then use three methodologies to evaluate model performance: human annotation, automated lexical-semantic metrics (ROUGE, Cosine Similarity, Jaccard), and model behavior diagnostics (prompt-level variance and across-model similarity). The results show that GPT gives the most coherent, semantically aligned, and contextually relevant answers; followed by Claude and Perplexity. Gemini and DeepSeek, on the other hand, have more variability and less agreement. Also, the similarity and stability of outputs change from company to company and over time, showing that they are sensitive to how prompts are written and what source material is used.
arxiv.org
August 1, 2025 at 5:18 AM
Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide variety of Financial Natural Language Processing (FinNLP) tasks. However, systematic comparisons among widely used LLMs remain underexplored. Given the rapid advancement and growing influence of LLMs in financial analysis, this study conducts a thorough comparative evaluation of five leading LLMs, GPT, Claude, Perplexity, Gemini and DeepSeek, using 10-K filings from the 'Magnificent Seven' technology companies. We create a set of domain-specific prompts and then use three methodologies to evaluate model performance: human annotation, automated lexical-semantic metrics (ROUGE, Cosine Similarity, Jaccard), and model behavior diagnostics (prompt-level variance and across-model similarity). The results show that GPT gives the most coherent, semantically aligned, and contextually relevant answers; followed by Claude and Perplexity. Gemini and DeepSeek, on the other hand, have more variability and less agreement. Also, the similarity and stability of outputs change from company to company and over time, showing that they are sensitive to how prompts are written and what source material is used.
arxiv.org
August 1, 2025 at 4:36 AM
FinNLP-FNP-LLMFinLegal 2025 : 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 Mo https://buff.ly/3OAsjDR
#callforpaper #wikicfp
FinNLP-FNP-LLMFinLegal Workshop at COLING-2025 Call For Papers(CFP)
Join the FinNLP-FNP-LLMFinLegal Workshop at COLING-2025 in Abu Dhabi, UAE, exploring financial technology, narrative processing, and large language models in fi...
buff.ly
December 6, 2024 at 6:25 PM
💬 We thank Dr. Chen for the thought-provoking talk and the discussion with UKP Lab members on language, mediation, and power in the age of #LLMs.

#UKPLab #NLProc #AIandSociety #ComputationalSocialScience #FinNLP #GuestTalk @tuda.bsky.social @cs-tudarmstadt.bsky.social
February 3, 2026 at 1:51 PM
Parag Pravin Dakle, Alolika Gon, Sihan Zha, Liang Wang, SaiKrishna Rallabandi, Preethi Raghavan
Jetsons at FinNLP 2024: Towards Understanding the ESG Impact of a News Article using Transformer-based Models
https://arxiv.org/abs/2404.00386
April 2, 2024 at 7:13 PM
📦 AI4Finance-Foundation / FinNLP
⭐ 369 (+50)
🗒 Jupyter Notebook

Democratizing Internet-scale financial data.
GitHub - AI4Finance-Foundation/FinNLP: Democratizing Internet-scale financial data.
Democratizing Internet-scale financial data. Contribute to AI4Finance-Foundation/FinNLP development by creating an account on GitHub.
github.com
June 20, 2023 at 11:58 PM