Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models
Summary
This paper introduces a retrieval-augmented LLM framework for financial sentiment analysis, achieving 15-48% improvement in accuracy and F1 score over traditional models and LLMs like ChatGPT and LLaMA.
View Cached Full Text
Cached at: 05/16/26, 12:24 PM
Paper page - Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models
Source: https://huggingface.co/papers/2310.04027
Abstract
A retrieval-augmented LLM framework improves financial sentiment analysis by tuning LLMs for sentiment prediction and augmenting them with external context, outperforming traditional models and other LLMs.
Financial sentiment analysisis critical for valuation and investment decision-making. Traditional NLP models, however, are limited by their parameter size and the scope of their training datasets, which hampers their generalization capabilities and effectiveness in this field. Recently, Large Language Models (LLMs) pre-trained on extensive corpora have demonstrated superior performance across various NLP tasks due to their commendablezero-shot abilities. Yet, directly applyingLLMsto financial sentiment analysis presents challenges: The discrepancy between the pre-training objective ofLLMsand predicting the sentiment label can compromise their predictive performance. Furthermore, the succinct nature of financial news, often devoid of sufficient context, can significantly diminish the reliability ofLLMs’ sentiment analysis. To address these challenges, we introduce a retrieval-augmentedLLMsframework forfinancial sentiment analysis. This framework includes aninstruction-tuned LLMsmodule, which ensuresLLMsbehave as predictors ofsentiment labels, and aretrieval-augmentationmodule which retrieves additional context from reliableexternal sources. Benchmarked against traditional models andLLMslike ChatGPT and LLaMA, our approach achieves 15\% to 48\% performance gain inaccuracyandF1 score.
View arXiv pageView PDFGitHub20.2kautoAdd to collection
Get this paper in your agent:
hf papers read 2310\.04027
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2310.04027 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2310.04027 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2310.04027 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Augmenting Fundamental Analysis with Large Language Models: A RAG-Based System for Generating Investor Briefs
This paper explores using LLMs with a RAG system to automate fundamental analysis of companies by processing financial reports and macroeconomic data, generating investor briefs evaluated by individual investors.
LLM-Based Financial Sentiment Analysis in Arabic: Evidence from Saudi Markets
This paper presents a framework for Arabic financial sentiment analysis using LLMs, tailored for the Saudi market, integrating news and social media data to capture investor sentiment.
Improving the Completeness and Comparability of Segment Disclosures: A Large Language Model Approach
This paper proposes an LLM-based framework to extract segment disclosures from 10-K filings, improving completeness and comparability through retrieval-augmented systems for longitudinal and cross-firm analysis.
Can Large Language Models Imitate Human Speech for Clinical Assessment? LLM-Driven Data Augmentation for Cognitive Score Prediction
This paper proposes a large language model-driven data augmentation framework using GPT-5 to generate synthetic oral monologues from written anchors for cognitive score prediction from speech. A similarity-guided selection strategy consistently reduces prediction error, particularly for minority low-score participants.
Evaluating LLM Usage for Efficient and Explainable Numerical and Classified Implicit Sentiment Analysis of Product Desirability
This paper presents a scalable framework using LLMs for implicit sentiment analysis of product desirability from qualitative feedback, achieving up to 0.97 Pearson correlation and 94% accuracy while providing explanations, with GPT-4o-mini offering similar performance at 94% lower cost.