AutoML-GPT uses GPT to automate AI model training.
problem Manual model selection and tuning requires significant human effort.
method Develops task-oriented prompts and utilizes LLMs for automated training.
result Achieves remarkable results in various AI tasks.
GPT learns a causal world model from token predictions, validated in game sequences.
problem Does GPT implicitly learn a causal world model from token predictions?
method Derived a causal interpretation of GPT's attention mechanism and proposed zero-shot causal structure learning.
result GPT can generate legal next moves with high confidence for sequences with encoded causal structures, but fails for illegal moves.
Large language models improve futures market factor models in China.
problem Designing effective factor models for Chinese futures markets.
method Used large language models (GPT) to generate 40 factors for single and multi-factor portfolios.
result GPT-generated factors outperform benchmarks with high Sharpe ratios and alphas.
Compact models match or exceed GPT's performance in financial news sentiment analysis.
problem Improving financial sentiment analysis models without large computational costs.
method Fine-tuning non-generative, small-sized models (FinBERT, FinDRoBERTa) on a novel market score database.
result Fine-tuned models outperform GPT-3.5 and GPT-4 in zero-shot learning for financial news sentiment analysis.
S 2 ^2 2 GPT-PINNs solve PDEs with sparse, small models.
problem Efficiently solving parametric PDEs with minimal resources.
method Sparse and small architecture, mathematically rigorous greedy algorithm, knowledge distillation, down-sampling.
result Achieves high efficiency with significantly fewer parameters.
ChatGPT models classify financial texts with minimal training.
problem Few-shot text classification in finance with limited labels.
method In-context learning with GPT-3.5 and GPT-4, fine-tuning with SetFit.
result GPT models outperform fine-tuned models with fewer examples.
GPT-4 improves stock price prediction from microblogging sentiments.
problem Improving stock price prediction using sentiment analysis of microblogs.
method Developed a novel method for contextual sentiment analysis using GPT-4, fine-tuning prompts for better accuracy.
result GPT-4 outperformed BERT in predicting stock price movements, achieving a peak accuracy of 71.47%.
GPT-GNN pre-trains GNNs on unlabeled graphs to improve downstream performance.
problem Training GNNs requires labeled data, which is expensive.
method Generative pre-training of GNNs on unlabeled data with self-supervision.
result GPT-GNN significantly outperforms state-of-the-art GNNs without pre-training.
Alpha-GPT mines new trading signals with human-AI interaction.
problem Mining new alphas for effective trading signals.
method Human-AI interaction and prompt engineering algorithmic framework.
result Demonstrates Alpha-GPT's effectiveness in generating creative, insightful, and effective alphas.
Study evaluates LLMs like ChatGPT and GPT-4 on financial analysis tasks.
problem Assessing financial reasoning capabilities of large language models.
method Mock CFA exam questions, Zero-Shot, Chain-of-Thought, Few-Shot scenarios.
result LLMs perform well on financial analysis tasks, but have limitations.
Alpha-GPT 2.0 integrates human insights into AI-driven investment research.
problem Efficiency and precision in quantitative investment research.
method Iterative Human-AI interaction using large language models.
result Enhanced efficiency and precision in quantitative investment research.
KM-GPT automates IPD reconstruction from KM plots with high accuracy and scalability.
problem Manual digitization of IPD from KM plots is error-prone and lacks scalability.
method KM-GPT integrates advanced image preprocessing, multi-modal reasoning, and iterative reconstruction algorithms.
result KM-GPT generates high-quality IPD without manual input or intervention, achieving superior accuracy.
Study compares AI models for stock price prediction using financial news.
problem Predicting stock price movements using financial news.
method Used FinBERT, GPT-4, and Logistic Regression for sentiment analysis and prediction.
result Logistic Regression outperformed FinBERT and GPT-4, achieving 81.83% accuracy.
Paper introduces TS-GPT for engineering time series forecasting.
problem Engineering time series require causal operations, unlike linguistic data.
method Innovations representation theory, Generative Pre-trained Transformer.
result TS-GPT effectively forecasts real-time locational marginal prices.
BERT models outperform GPT in financial engineering sentiment analysis.
problem Using sentiment from news events for commodity trading.
method Benchmarked Transformer models (BERT, GPT) on financial engineering task.
result CopBERT models outperform GPT and vanilla BERT models.
In this work, we focus on fine-tuning an OpenAI GPT-2 pre-trained model for generating patent claims. GPT-2 has demonstrated impressive efficacy of pre-trained language models on various tasks, particularly coherent text generation. Patent claim language itself has rarely been explored in the past and poses a unique ch…
SusGen-GPT improves financial NLP and ESG report generation.
problem Lack of advanced NLP tools for finance and ESG domains.
method Developed SusGen-30K dataset and SusGen-GPT models.
result Achieved state-of-the-art performance in financial NLP tasks.
GPT-f uses language models to find new proofs in formal math.
problem Generating original mathematical terms for automated theorem proving.
method Transformer-based language model for automated theorem proving and proof assistant.
result GPT-f contributed new proofs to the Metamath library.
Study shows GPT's earnings forecasts are human-like but not always accurate.
problem Information friction in AI-generated financial analysis.
method Examined GPT's earnings forecasts following corporate earnings releases and proposed a diagnostic framework.
result GPT's narrative attention is consistent and human-like but not always associated with higher forecast accuracy.
GPT-4 assesses its confidence in answering USMLE questions with and without feedback.
problem Understanding AI's performance in healthcare applications, especially in sensitive areas like medical education.
method Used a prompting technique to evaluate GPT-4's confidence scores before and after answering USMLE questions, categorized into with and without feedback.
result Feedback influences relative confidence but doesn't consistently increase or decrease it.
MarketGPT models financial time series with realistic order flow data.
problem Creating accurate financial market simulations.
method Generative pre-trained transformer (GPT) for long sequence generation.
result Model reproduces key features of real financial markets and stylized facts.
GPT model shows promise in financial market predictions.
problem Challenges in predicting stock market movements due to noisy data.
method Comparing GPT model with BERT model using Federal Reserve Beige Book data.
result GPT model has look-ahead bias, traditional models still perform better.
We present an open-source tool for visualizing multi-head self-attention in Transformer-based language representation models. The tool extends earlier work by visualizing attention at three levels of granularity: the attention-head level, the model level, and the neuron level. We describe how each of these views can he…
DARE uses GPT-2 to generate relation examples, improving RE performance.
problem Challenges in Relation Extraction, especially limited data and class imbalance.
method Data augmentation with GPT-2 fine-tuning to generate relation examples.
result Improves RE performance by up to 11 F1 score points.
Generates natural product-like compounds using GPT models.
problem Challenges in generating and evaluating natural product-like compounds.
method Trained GPT-based chemical language models on natural product dataset.
result Generated compounds have similar distribution to natural products.
Project aims to improve coherence in language generation models.
problem Models often generate inconsistent text that diverges from the prompt.
method Trained a sentence pair coherence classifier and co-trained GPT-2 with this coherence objective.
result Fine-tuned model generates coherent paragraphs without diverging.
Transformer models improve arithmetic accuracy with number decomposition.
problem Transformer models struggle with arithmetic operations without decomposition.
method Fine-tuning models with a pipeline that decomposes numbers into units, tens, etc.
result Accuracy increased by 63% in five-digit addition tasks.
KodeXv0.1 improves financial question answering over GPT-4.
problem Lack of specialized financial language models.
method Custom training on financial documents, RAG-aware 4bit LoRA tuning.
result KodeX-8Bv0.1 outperforms GPT-4 by up to 9.24% in financial tasks.
New algorithms improve privacy and utility of large language models.
problem Privacy-preserving fine-tuning of large language models.
method Meta-framework for differentially private fine-tuning, inspired by recent success in fine-tuning.
result Private fine-tuned models achieve utility close to non-private models, with improved privacy and efficiency.
Large language models predict human sensory judgments across multiple modalities.
problem Determining the extent of perceptual information in language.
method State-of-the-art large language models were used to predict sensory judgments across six psychophysical datasets.
result Large language models can predict human sensory judgments across multiple modalities with significant correlation to human data.
Study benchmarks LLMs in portfolio optimization tasks.
problem Evaluate financial decision-making of LLMs.
method Mathematically explicit portfolio optimization problems with multiple-choice questions.
result Distinct performance patterns among LLMs in different financial tasks.
BatchTopK SAEs improve GPT-2 and Gemma activations with adjustable sparsity.
problem Interpreting language model activations using sparse autoencoders.
method Adapting the TopK constraint to the batch-level, allowing variable number of active latents per sample.
result BatchTopK SAEs consistently outperform TopK SAEs in reconstructing GPT-2 and Gemma activations.
Random feature models can outperform a weak teacher with early stopping.
problem Generalization from a weak to a strong model in random feature networks.
method Random feature models, early stopping, proving weak-to-strong generalization.
result Random feature models can outperform a weak teacher with early stopping.
Improved differentially private deep learning with group-wise clipping techniques.
problem Efficiency and privacy trade-offs in deep learning models.
method Group-wise clipping techniques (per-layer and per-device) to reduce compute time and memory overhead.
result Private learning with group-wise clipping achieves similar or better performance than non-private learning with less wall time.
LLMs improve financial sentiment analysis in finance.
problem Defining and measuring financial sentiment.
method Investigation of sentiment measurement methods and LLMs.
result LLMs enhance financial sentiment analysis.
nGPT learns to transfer learning rates across model dimensions and token horizons.
problem nGPT does not transfer learning rates across model size and token horizon.
method Combining numerical experiments with alignment exponents, a novel nGPT parameterization νGPT is developed.
result νGPT exhibits learning rate transfer across width, depth, and token horizon.
National statistical systems are the enterprises tasked with collecting, validating and reporting societal attributes. These data serve many purposes - they allow governments to improve services, economic actors to traverse markets, and academics to assess social theories. National statistical systems vary in quality, …
FinanceBench benchmarks LLMs on financial QA, revealing limitations.
problem Evaluating LLMs' performance on financial question answering.
method Developed a comprehensive test suite (FinanceBench) with 10,231 questions, tested 16 models, and manually reviewed answers.
result Existing LLMs have significant limitations for financial QA, especially GPT-4-Turbo.
This paper evaluates LLMs for technical market analysis, finding GPT-4 Turbo and FinGPT outperform passive benchmarks.
problem Evaluating LLMs for technical market analysis in financial markets.
method Structured evaluation of five LLMs (GPT-4 Turbo, Claude 3 Opus, Gemini 1.5 Pro, Llama 3 70B, FinGPT) on four tasks: candlestick pattern recognition, directional signal generation, backtesting, and financial report comprehension.
result GPT-4 Turbo and FinGPT outperform passive benchmarks in simulated backtesting, with GPT-4 Turbo achieving the highest annualized return and Sharpe ratio.
ChatGPT predicts stock market reactions from news headlines without financial training.
problem Predicting stock price movements using non-financial data.
method Used post-knowledge-cutoff headlines to train ChatGPT-4, which forecasts stock market reactions.
result ChatGPT-4 can predict stock market reactions with high accuracy, especially for small stocks and negative news.
FraudTransformer detects payment fraud by preserving event order and time gaps.
problem Detecting payment fraud in real-world banking streams with irregular time gaps.
method Augments a GPT-style architecture with a dedicated time encoder and a learned positional encoder.
result FraudTransformer outperforms classical and transformer baselines, achieving highest AUROC and PRAUC on held-out test set.
Pre-trained LLM adapted with LoRA improves offline RL for quantitative trading.
problem Challenges in offline RL for quantitative trading due to complex temporal dependencies and overfitting.
method Integrates pre-trained GPT-2 weights and LoRA for efficient fine-tuning of a Decision Transformer.
result Outperforms existing offline RL methods in certain trading scenarios.
The study analyzes how large language models form and express investor risk profiles.
problem Understanding how large language models (LLMs) form and express investor risk profiles.
method Examined three LLMs (GPT, Gemini, and Llama) and assessed their responses to a standardized risk questionnaire under varying prompts.
result LLMs generally form long-term investment profiles, but they exhibit different risk tolerance levels.
Study assesses consistency and reproducibility of LLMs in finance and accounting tasks.
problem Consistency and reproducibility of LLM outputs in finance and accounting research.
method Extensive experimentation with 50 independent runs across 5 tasks using 3 OpenAI models.
result Task-specific patterns of consistency and reproducibility, with binary classification and sentiment analysis achieving near-perfect reproducibility.
New algorithms speed up attention computation for large models by limiting matrix entries.
problem Efficiently compute attention matrices for large language models.
method Developed algorithms that exploit the structure of the attention matrix A A A to achieve subquadratic time complexity. result There is a sharp transition at B = Θ ( log n ) B = Θ(\sqrt{\log n}) B = Θ ( log n ) for efficient computation of attention matrices. Foundation models leak sensitive data in synthetic tabular data generation, especially LLaMA 3.3 70B.
problem Privacy leakage in synthetic tabular data generation using foundation models.
method Benchmarked three foundation models (GPT-4o-mini, LLaMA 3.3 70B, TabPFN v2) against four baselines on 35 real-world tables.
result Foundation models, especially LLaMA 3.3 70B, have the highest privacy risk in synthetic tabular data generation.
Simple adaptive attacks can jailbreak state-of-the-art safety-aligned language models.
problem Vulnerability of safety-aligned language models to simple adaptive attacks.
method Designing adversarial prompt templates, random search on suffixes, and transfer/prefilling attacks.
result 100% attack success rate on various models including GPT-4, Vicuna, Mistral, and Claude.
Reasoning models outperform LLMs on CFA exams.
problem Previous research showed LLMs failing CFA exams; reasoning models show promise.
method Evaluated state-of-the-art reasoning models on CFA exams using pass/fail criteria.
result Most reasoning models pass all three CFA levels; Gemini 3.0 Pro achieves highest scores.