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.

168,657 papers · 148 categories

Trend · papers per month

1234 · May 202319922001200920172026
48 results for GPT-4

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%.

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.

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.

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.

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.

The paper certifies AI reliability via sampling and calibration, providing exact guarantees.

problem Ensuring trust in black-box AI systems' outputs.
method Self-consistency sampling and conformal calibration.
result Reliability levels derived from these methods offer finite-sample guarantees.

ChemCrow enhances LLMs for chemistry tasks, automating complex chemical processes.

problem Limited access to computational chemistry tools for large-language models.
method Integrating 18 expert-designed chemistry tools into an LLM (ChemCrow).
result ChemCrow autonomously plans and executes chemical syntheses and discoveries.

This paper explores how LLMs can improve pipeline-based conversational agents.

problem Limitations of pipeline-based conversational agents in human-like conversations.
method Investigated LLMs' capabilities in two phases: design and development, and operations.
result LLMs can enhance pipeline-based agents in various tasks like data generation, intent classification, and auto-correction.

Paper uses LLMs for financial forecasting, overcoming sequence reasoning and multi-modal challenges.

problem Challenges in financial time series forecasting, especially cross-sequence reasoning and multi-modal signals.
method Combines LLMs with financial data and news, using zero-shot/few-shot inference and instruction-based fine-tuning.
result LLMs can offer explainable financial forecasts, leveraging cross-sequence reasoning and multi-modal information.

SPPO optimizes language model alignment by treating preferences as a game and achieving state-of-the-art performance.

problem Capturing intransitivity and irrationality in human preferences for accurate language model alignment.
method Self-play-based approach to identify Nash equilibrium policy through iterative policy updates.
result SPPO achieves state-of-the-art win-rate of 28.53% on AlpacaEval 2.0 without external supervision.

LATM framework uses LLMs to create and reuse tools for efficient problem-solving.

problem Improving problem-solving capabilities of LLMs with external tools.
method Closed-loop framework with two phases: tool making and tool using. LLMs act as both tool makers and users. Resource-intensive model for tool making, lightweight model for tool using.
result LATM framework achieves performance equivalent to using a powerful LLM for both roles but with significantly reduced costs.

Enhanced stock market strategy using stress index and financial news sentiment analysis.

problem Improving risk assessment and prediction in equity markets.
method Combines financial stress indicator with sentiment analysis of financial news.
result Improved performance with higher Sharpe ratio and reduced drawdowns.

This study analyzes financial equity research reports to identify frequently asked questions and automates 80% of them.

problem Insufficient empirical analysis of questions answered in financial equity research reports.
method Analyzed 72 financial equity research reports, classifying sentences into 169 unique question archetypes. Used public corporate reports to classify questions' potential for automation.
result Approximately 80% of financial equity research reports can be automated, with 78.7% of questions automatable.

LLMs can help explain credit risk models but not autonomously.

problem Leveraging LLMs for post-hoc explainability in credit risk models.
method Comparison of LLM outputs with SHAP and coefficient-based attributions on three LMs.
result LLMs reliably preserve feature-importance rankings but poorly align with autonomous explanations.

ZeroSCROLLS benchmarks zero-shot natural language understanding over long texts.

problem Evaluate natural language understanding models over long texts without training data.
method Adapt six tasks from SCROLLS benchmark and add four new datasets, including novel aggregation tasks.
result Claude outperforms ChatGPT, and GPT-4 achieves highest average score.

Caus-Modens uses deep ensembles to better predict causal outcomes in hidden confounding scenarios.

problem Predicting causal outcomes in the presence of hidden confounders.
method Caus-Modens employs a modulated ensemble approach to improve prediction intervals for causal outcomes using sensitivity models.
result Caus-Modens provides tighter prediction intervals for causal outcomes compared to existing methods.

Randomized Geometric Algebra for Convex Neural Networks Optimizes Transfer Learning.

problem Training neural networks to global optimality via convex optimization.
method Randomized algorithms in Clifford's Geometric Algebra for hypercomplex vector spaces.
result Convex optimization and geometric algebra improve LLMs' robustness and reliability in transfer learning.

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.

Adaptive testing segments watermarked text from LLMs.

problem Distinguishing LLM-generated text from human-written content.
method Generalized likelihood-based detection method adapted to inverse transform sampling, removing prompt estimation sensitivity.
result Effective and robust method for segmenting watermarked text.

Ploutos predicts stock movements with financial LLM, improving interpretability.

problem Combining textual and numerical data for stock prediction and lack of interpretability.
method Proposes Ploutos framework combining PloutosGen and PloutosGPT for interpretable predictions.
result Framework outperforms state-of-the-art methods in prediction accuracy and interpretability.

The paper proposes a method to evaluate superhuman models by checking for logical inconsistencies.

problem Evaluating superhuman models when ground truth is hard to obtain.
method A framework using consistency checks to identify logical inconsistencies in model decisions.
result Logical inconsistencies can be discovered in superhuman model decisions across various tasks.

Enhances stock return prediction using LLMs and hybrid models.

problem Insufficient use of semantic information and alignment of LLMs with stock features.
method LG model with three strategies for global information modeling and SCRL for embedding alignment.
result Superior performance in Rank Information Coefficient and returns compared to models relying only on stock features.

Transformers learn to generalize unseen tasks by composing self-attention layers.

problem How Transformers generalize to unseen, out-of-distribution tasks.
method Examined synthetic examples and pretrained LLMs, focusing on induction heads and latent subspace.
result Transformers can learn hidden rules for unseen tasks by composing self-attention layers, achieving OOD generalization.

This paper strengthens the computational separation between multimodal and unimodal learning, showing unimodal learning is hard on typical instances.

problem Theoretical justification for empirical success of multimodal machine learning.
method Introduced a stronger average-case computational separation between unimodal and multimodal learning.
result For typical instances, unimodal learning is computationally hard, while multimodal learning is easy.

Robots' agility in changing terrain helps financial models adapt to market shifts.

problem Challenges in financial market forecasting due to regime switching.
method Adapts pretrained LLMs using intrinsic market rewards and reinforcement learning.
result Significantly improved accuracy in adapting to market regime shifts.