Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models

Papers with Code Trending Papers

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.

Financial sentiment analysis is 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 commendable zero-shot abilities. Yet, directly applying LLMs to financial sentiment analysis presents challenges: The discrepancy between the pre-training objective of LLMs and 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 of LLMs' sentiment analysis. To address these challenges, we introduce a retrieval-augmented LLMs framework for financial sentiment analysis. This framework includes an instruction-tuned LLMs module, which ensures LLMs behave as predictors of sentiment labels, and a retrieval-augmentation module which retrieves additional context from reliable external sources. Benchmarked against traditional models and LLMs like ChatGPT and LLaMA, our approach achieves 15\% to 48\% performance gain in accuracy and F1 score.
Original Article
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

Can LLMs Take Retrieved Information with a Grain of Salt?

arXiv cs.CL

This paper investigates how large language models adapt to the certainty of retrieved information, identifying systematic limitations in handling uncertainty. It proposes an interaction strategy that reduces obedience errors by 25% without modifying model weights.