Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Feb 199419922001200920172026
48 results for GPT model

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.

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.

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%.

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.

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…

2019-07-01abs ↗pdf ↗

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.

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.

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.

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.

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.

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 AA to achieve subquadratic time complexity.
result There is a sharp transition at B=Θ(logn)B = Θ(\sqrt{\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.