FinBERT
PulseAugur coverage of FinBERT — every cluster mentioning FinBERT across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Build Your Own AI Trading Bot with Trader-GPT and Python
This article details the creation of a generative AI-powered trading bot, dubbed Trader-GPT. It outlines the current landscape, noting increased interest in AI trading bots and the availability of mature LLMs like GPT-4…
-
New attack framework reveals critical semantic insensitivity in financial AI models
A new research paper introduces Agent-driven Semantic Inversion (ASI), a framework designed to test the robustness of financial sentiment analysis models. The study found that FinBERT, a widely used model, was deceived …
-
NoLBERT-Calls model mitigates hindsight bias in earnings call analysis
Researchers have developed NoLBERT-Calls, a novel approach to analyzing earnings call transcripts that mitigates the issue of hindsight bias in language models. By pre-training an encoder on data exclusively from 1976-1…
-
LLMs in finance: Balancing model size, cost, and accuracy
The use of large language models (LLMs) in finance presents challenges beyond model performance, focusing on deployment, cost, and accountability. Smaller, domain-specific models like FinBERT, adapted for financial text…
-
NoLBERT model trained on historical news aims to reduce stock market prediction bias
Researchers developed NoLBERT, a language model trained on historical financial news from 1976-1995, to mitigate hindsight bias in stock market predictions. They compared NoLBERT's topics with those from LDA, MiniLM, an…
-
New study questions validity of financial NLP tools against human judgment
A new arXiv paper investigates the validity of financial Natural Language Processing (NLP) tools by comparing their ability to extract market signals against human judgment. The study analyzed over 70,500 X messages lin…
-
Financial NLP benchmarks suffer from temporal leakage, inflating performance metrics
A new audit of financial news NLP benchmarks reveals significant temporal leakage, where random train-test splits inflate performance metrics by up to 6.5x compared to chronological splits. This leakage is particularly …
-
New RA-FinBERT model boosts financial sentiment analysis with rule-based features
Researchers have developed RA-FinBERT, a novel framework for financial sentiment analysis that enhances accuracy by integrating rule-derived features with a pre-trained language model. This approach combines sentiment p…
-
LLMs Show High Accuracy in Financial Sentiment, But Fail to Predict Stock Returns
A new study benchmarks several large language models (LLMs) for their effectiveness in financial sentiment classification and return predictability. Researchers found that while models like Mistral-7B and QLoRA-adapted …
-
LLaMA-3.1-70B extracts structured data from financial news to boost stock prediction
Researchers have developed a new framework for extracting structured information from financial news, moving beyond traditional sentiment analysis. This framework utilizes LLaMA-3.1-70B to identify six semantic dimensio…
-
AI system AWARE-FX quantifies FX hedging disclosures in corporate reports
Researchers have developed AWARE-FX, an AI system designed to analyze corporate annual reports and quantify foreign-exchange hedging disclosures. This system integrates a specialized lexicon, logic for negation and acco…
-
New AI Model RAML Improves Bitcoin Price Prediction Using Dynamic Sentiment Fusion
Researchers have developed a new model called Regime-Aware Multi-Modal Learning (RAML) to predict Bitcoin price movements on sub-daily timescales. Unlike traditional methods that statically combine price and social sent…
-
TriAgent cuts LLM costs for financial sentiment analysis
Researchers have developed TriAgent, a novel multi-agent system designed to reduce the cost of financial sentiment analysis using large language models. The system stratifies agents by contextual granularity, employing …
-
Domain adaptation efficacy depends on pre-trained model's domain knowledge
A new study investigates the effectiveness of domain adaptation techniques when using frozen pre-trained language model backbones for sentiment analysis. The research evaluated different adaptation methods like DANN, MM…
-
New AI Framework Enhances Audit Risk Assessment with Uncertainty Modeling
Researchers have developed UMAR, a novel multi-agent framework designed to improve audit risk assessment by explicitly modeling uncertainty and evidence conflict. UMAR utilizes three specialized agents—MD&A Text Agent, …
-
New method uses FinBERT embeddings for better stock market prediction
Researchers have developed a new method to improve financial forecasting by using high-dimensional embeddings from FinBERT instead of simple sentiment scores. Their Transformer-based architecture, which incorporates Sia…
-
Deep Learning Models Predict Stock Price Direction Using Multi-modal Data
Researchers have developed a multi-modal deep learning approach to predict stock price direction on earnings announcement days. The study combines fundamental metrics, technical indicators, and sentiment analysis from f…
-
Researchers aggregate zero-shot LLM outputs for better stock return prediction
Researchers have developed a lightweight supervised aggregator to combine outputs from multiple zero-shot Large Language Models (LLMs) for classifying corporate disclosures. This method aims to improve prediction accura…