Beyond Surface Similarity: Detecting Subtle Semantic Shifts in Financial Narratives

• URL: http://arxiv.org/abs/2403.14341v1
• Date: Thu, 21 Mar 2024 12:17:59 GMT
• Title: Beyond Surface Similarity: Detecting Subtle Semantic Shifts in Financial Narratives
• Authors: Jiaxin Liu, Yi Yang, Kar Yan Tam,
• Abstract summary: We introduce the Financial-STS task, a financial domain-specific NLP task designed to measure the nuanced semantic similarity between pairs of financial narratives. Measuring the subtle semantic differences between these paired narratives enables market stakeholders to gauge changes over time in the company's financial and operational situations.
• Score: 19.574432889355627
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we introduce the Financial-STS task, a financial domain-specific NLP task designed to measure the nuanced semantic similarity between pairs of financial narratives. These narratives originate from the financial statements of the same company but correspond to different periods, such as year-over-year comparisons. Measuring the subtle semantic differences between these paired narratives enables market stakeholders to gauge changes over time in the company's financial and operational situations, which is critical for financial decision-making. We find that existing pretrained embedding models and LLM embeddings fall short in discerning these subtle financial narrative shifts. To address this gap, we propose an LLM-augmented pipeline specifically designed for the Financial-STS task. Evaluation on a human-annotated dataset demonstrates that our proposed method outperforms existing methods trained on classic STS tasks and generic LLM embeddings.

Related papers

• Advancing Anomaly Detection: Non-Semantic Financial Data Encoding with LLMs [49.57641083688934]
  We introduce a novel approach to anomaly detection in financial data using Large Language Models (LLMs) embeddings. Our experiments demonstrate that LLMs contribute valuable information to anomaly detection as our models outperform the baselines.
  arXiv  Detail & Related papers  (2024-06-05T20:19:09Z)
• Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model [50.339632513018934]
  supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language model (LLM) to specific preferences. We critically examine this hypothesis within the scope of cross-lingual generation tasks. We introduce a novel training-free alignment method named PreTTY, which employs minimal task-related prior tokens.
  arXiv  Detail & Related papers  (2024-04-25T17:19:36Z)
• Multi-Task Learning for Features Extraction in Financial Annual Reports [6.442186704634672]
  We use various multi-task learning methods for financial text classification. We focus on financial sentiment, objectivity, forward-looking sentence prediction and ESG-content detection. We extract textual features from annual reports of FTSE350 companies and investigate the link between ESG quantitative scores and these features.
  arXiv  Detail & Related papers  (2024-04-08T08:13:40Z)
• Large Language Model Adaptation for Financial Sentiment Analysis [2.0499240875882]
  Generalist language models tend to fall short in tasks specifically tailored for finance. Two foundation models with less than 1.5B parameters have been adapted using a wide range of strategies. We show that small LLMs have comparable performance to larger scale models, while being more efficient in terms of parameters and data.
  arXiv  Detail & Related papers  (2024-01-26T11:04:01Z)
• Designing Heterogeneous LLM Agents for Financial Sentiment Analysis [0.8158530638728501]
  This study investigates the effectiveness of large language models (LLMs) in financial sentiment analysis (FSA) Rooted in Minsky's theory of mind and emotions, a design framework with heterogeneous LLM agents is proposed. The framework instantiates specialized agents using prior domain knowledge of the types of FSA errors and reasons on the aggregated agent discussions.
  arXiv  Detail & Related papers  (2024-01-11T10:06:42Z)
• PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance [63.51545277822702]
  PIXIU is a comprehensive framework including the first financial large language model (LLMs) based on fine-tuning LLaMA with instruction data. We propose FinMA by fine-tuning LLaMA with the constructed dataset to be able to follow instructions for various financial tasks. We conduct a detailed analysis of FinMA and several existing LLMs, uncovering their strengths and weaknesses in handling critical financial tasks.
  arXiv  Detail & Related papers  (2023-06-08T14:20:29Z)
• Flexible categorization for auditing using formal concept analysis and Dempster-Shafer theory [55.878249096379804]
  We study different ways to categorize according to different extents of interest in different financial accounts. The framework developed in this paper provides a formal ground to obtain and study explainable categorizations.
  arXiv  Detail & Related papers  (2022-10-31T13:49:16Z)
• Stock Embeddings: Learning Distributed Representations for Financial Assets [11.67728795230542]
  We propose a neural model for training stock embeddings, which harnesses the dynamics of historical returns data. We describe our approach in detail and discuss a number of ways that it can be used in the financial domain.
  arXiv  Detail & Related papers  (2022-02-14T15:39:06Z)
• FinEAS: Financial Embedding Analysis of Sentiment [0.0]
  We introduce a new language representation model in finance called Financial Embedding Analysis of Sentiment (FinEAS) In this work, we propose a new model for financial sentiment analysis based on supervised fine-tuned sentence embeddings from a standard BERT model.
  arXiv  Detail & Related papers  (2021-10-31T15:41:56Z)
• Similarity metrics for Different Market Scenarios in Abides [58.720142291102135]
  Markov Decision Processes (MDPs) are an effective way to formally describe many Machine Learning problems. This paper analyzes the use of three similarity metrics based on conceptual, structural and performance aspects of the financial MDPs.
  arXiv  Detail & Related papers  (2021-07-20T09:18:06Z)
• Gaussian process imputation of multiple financial series [71.08576457371433]
  Multiple time series such as financial indicators, stock prices and exchange rates are strongly coupled due to their dependence on the latent state of the market. We focus on learning the relationships among financial time series by modelling them through a multi-output Gaussian process.
  arXiv  Detail & Related papers  (2020-02-11T19:18:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.