REVIEW 16 cited by
FinBERT: A Pretrained Language Model for Financial Communications
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Contextual pretrained language models, such as BERT (Devlin et al., 2019), have made significant breakthrough in various NLP tasks by training on large scale of unlabeled text re-sources.Financial sector also accumulates large amount of financial communication text.However, there is no pretrained finance specific language models available. In this work,we address the need by pretraining a financial domain specific BERT models, FinBERT, using a large scale of financial communication corpora. Experiments on three financial sentiment classification tasks confirm the advantage of FinBERT over generic domain BERT model. The code and pretrained models are available at https://github.com/yya518/FinBERT. We hope this will be useful for practitioners and researchers working on financial NLP tasks.
Forward citations
Cited by 16 Pith papers
-
AWARE-FX: An Auditable Knowledge-Guided AI System for Measuring Corporate Foreign-Exchange Hedging Disclosure
An auditable NLP pipeline scores FX hedging disclosure from 24,909 Hong Kong firm-years; its strict score, unlike generic hedging text, tracks firms' FX exposure.
-
FinAbstain: Uncertainty-Calibrated Multimodal RAG for Selective Financial Forecasting
A multimodal RAG system with point-in-time retrieval and calibrated abstention is presented, with only simulated evidence that refusal reduces selective error and drawdown.
-
Masked Autoencoders for Ultrasound Signals: Robust Representation Learning for Downstream Applications
MAE pre-training on synthetic ultrasound signals transfers to real measured signals and beats from-scratch and CNN baselines on time-of-flight classification, with the biggest gains in low-label regimes.
-
FinGAIA: A Chinese Benchmark for AI Agents in Real-World Financial Domain
FinGAIA is a 407-task Chinese financial agent benchmark where the best agent, ChatGPT DeepResearch, scores 48.9%, far below financial experts at 84.7%.
-
Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching
A flipped distillation method lets a decoder-only LLM learn text-matching similarity from a smaller encoder teacher through LoRA and a margin-aware contrastive loss, improving matching accuracy and online FAQ retrieval.
-
NewsNet-SDF: Stochastic Discount Factor Estimation with Pretrained Language Model News Embeddings via Adversarial Networks
A neural stochastic discount factor that reads news text through a pretrained language model and macro data through an LSTM reports out-of-sample Sharpe 2.80 on US equities from 2000 to 2022.
-
Automated Retrosynthesis Planning of Macromolecules Using Large Language Models and Knowledge Graphs
An LLM-and-knowledge-graph agent automatically constructs retrosynthetic pathway trees for macromolecules and recommends optimal synthesis routes, demonstrated on polyimide.
-
TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis
A divergence-routed VADER+FinBERT+LLM committee reaches ~0.87 F1 with a 1.5B critic, matching 7B with far less cost, while same-size persona voting regresses to 0.66.
-
Evaluating Financial Sentiment Analysis with Annotators Instruction Assisted Prompting: Enhancing Contextual Interpretation and Stock Prediction Accuracy
Adding annotators' instructions to the prompt raises LLM financial sentiment accuracy on a new WallStreetBets dataset by an average of 5.90 percent, and a confidence-based sentiment score helps stock prediction on som...
-
FinSphere, a Real-Time Stock Analysis Agent Powered by Instruction-Tuned LLMs and Domain Tools
FinSphere, an instruction-tuned Qwen2-72B agent with real-time quantitative tools, scores 70.88/100 on the authors' human rubric, ahead of FinMem (67.55) and GPT-4o (66.61) on 100 queries.
-
INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent
InvestorBench evaluates 13 large language models as trading agents on stock, crypto, and ETF tasks, reporting that proprietary models beat open-source ones on average.
-
Bitcoin Price Direction Prediction via Regime-Aware Multi-Modal Fusion of Social Sentiment and Technical Features
A regime-gated sentiment/price fusion model for hourly Bitcoin direction prediction achieves near-random accuracy (AUC 0.5084 at 3h), and its key claims are contradicted by its own results.
-
Adaptive Minds: Empowering Agents with LoRA-as-Tools
Adaptive Minds makes a base LLM select LoRA adapters as tools per query; the 5-adapter demo gets 100% routing on 25 queries, while the abstract's 30-adapter/nine-family numbers are unsupported.
-
Towards Automated Regulatory Compliance Verification in Financial Auditing with Large Language Models
In a small evaluation with PwC data, Llama-2-70b beats GPT models at the 'no compliance' class for IFRS reports, but the result is based on a single selected prompt and a 100-item sample, and the data/code are not released.
-
FinAI-BERT: A Transformer-Based Model for Sentence-Level Detection of AI Disclosures in Financial Reports
A BERT model fine-tuned to detect AI-related sentences in bank annual reports, reporting 99% accuracy, but the evaluation is compromised by lexicon-derived labels and inconsistent statistics.
-
Enhancing Trading Performance Through Sentiment Analysis with Large Language Models: Evidence from the S&P 500
A backtest over May-August 2024 claims that adding GPT-2 and FinBERT news sentiment to technical indicators improves S&P 500 trading returns, with a best reported return of 5.77%.
Discussion (0). Continue with ORCID to comment.