The paper optimizes LLM accuracy by stopping early based on consistent answers.
problem Improving LLM accuracy in math and reasoning problems.
method Bayesian stopping policy to save on sampling costs, tracking only the L-1 most frequent answer counts.
result The L=3 stopping policy is sufficient for asymptotic optimality and significantly reduces inference costs.
BC-LLM uses LLMs to find concepts without predefined sets, improving interpretability and performance.
problem Finding a balance between interpretability and accuracy in concept extraction models.
method Bayesian approach with LLMs as both concept extractor and prior.
result BC-LLM outperforms interpretable and black-box models across various datasets.
LaRT models LLMs' response accuracy and CoT length to evaluate reasoning ability and speed.
problem Valid evaluation of Large Language Models (LLMs) via response accuracy and chain-of-thought length.
method Introduces Latency-Response Theory (LaRT) to jointly model response accuracy and CoT length using latent ability and latent speed.
result LaRT yields higher estimation accuracy and shorter confidence intervals for latent traits compared to IRT.
CrowdLLM uses LLMs and generative models to create diverse digital populations.
problem Lack of diversity and accuracy in digital populations created by LLMs.
method Integrates pretrained LLMs and generative models to enhance diversity and fidelity.
result CrowdLLM achieves promising performance in accuracy and distributional fidelity.
Study evaluates how much knowledge LLMs have by comparing their prediction accuracy to flexible models.
problem Evaluating the predictive power of LLMs without access to their training data.
method Equivalent sample size measure, comparing LLM's prediction error to flexible models trained on varying amounts of domain-specific data.
result LLMs encode varying amounts of predictive information across different economic variables.
CROQ optimizes LLM decision-making by narrowing down choices and improving accuracy.
problem Uncertainty in LLM outputs poses risks in high-stakes domains.
method Conformal prediction (CP) and optimization (CP-OPT) to minimize prediction set sizes.
result CROQ improves LLM accuracy, especially with CP-OPT.
We detect lookahead bias in LLM forecasts using a novel statistical method.
problem Detecting lookahead bias in LLM-generated economic forecasts.
method Developed a statistical procedure using date-only recall queries and estimated Lookahead Propensity (LAP).
result LLM forecasts are contaminated with lookahead bias, as indicated by a positive interaction between LAP and the forecast in accuracy regressions.
RACER optimizes LLM-as-judge accuracy with dynamic reasoning selection.
problem Balancing reasoning accuracy with computational cost in LLM-as-judge settings.
method Formulates routing as a constrained distributionally robust optimization problem, accounting for distribution shift via KL-divergence uncertainty set.
result RACER achieves superior accuracy-cost trade-offs under distribution shift.
New benchmarks show LLMs struggle with causal discovery.
problem Leveraging LLMs for causal discovery is unreliable due to dataset leakage.
method Developing science-grounded benchmarks and hybrid methods combining LLM predictions with statistical analysis.
result LLMs perform poorly on novel, real-world scientific studies compared to classical methods.
LOLA uses LLMs to optimize content delivery, outperforming traditional methods.
problem Identifying the most engaging headlines for user engagement.
method LOLA integrates LLMs with adaptive experimentation to optimize content delivery.
result LOLA outperforms traditional methods in optimizing user engagement.
Dynamic abstention improves LLM accuracy by selectively terminating unpromising reasoning.
problem LLMs waste compute on incorrect responses, leading to inefficiency.
method Formal reinforcement learning framework with abstention reward parameter.
result Dynamic abstention outperforms natural baselines in selective accuracy.
THERMOMETER calibrates LLMs efficiently for diverse tasks.
problem Calibrating large language models is challenging due to computational and versatility issues.
method THERMOMETER learns an auxiliary model for calibrating a LLM using data from multiple tasks.
result THERMOMETER produces better-calibrated responses for new tasks.
LLMs can predict CFO responses to economic surveys
problem Measuring business sentiment
method Prompting an LLM to role-play as a CFO
result LLM reproduces individual human responses
FLUID-LLM uses LLMs to predict fluid dynamics with improved accuracy.
problem Leveraging LLMs for CFD due to their pattern recognition abilities but struggles with fluid dynamics complexities.
method Combines pre-trained LLMs with spatiotemporal-aware encoding to predict unsteady fluid dynamics.
result Significant performance improvements in CFD predictions across various datasets.
Study shows awareness of reflexivity improves LLMs' financial forecasting accuracy.
problem Improving LLMs' ability to forecast financial markets during boom-bust cycles.
method Evaluated three LLMs under four conditions of reflexivity awareness in two market episodes.
result Reflexivity awareness improves forecasting accuracy differently across models and contexts.
New benchmarks focus on LLM risk in finance, not just accuracy.
problem Standard benchmarks ignore LLM financial risks, leading to unsafe deployment.
method Three-level agenda: model, workflow, and system stress-testing.
result Hidden weaknesses in LLMs are missed by traditional benchmarks.
FinMaster benchmarks LLMs in financial tasks, revealing gaps in reasoning.
problem Challenges in financial tasks, including labor-intensive processes and low error tolerance.
method Developed a comprehensive financial benchmark (FinMaster) with three modules: FinSim, FinSuite, and FinEval.
result LLMs struggle with complex financial reasoning, showing significant accuracy drops.
Unified framework to bridge human and LLM judgments.
problem Systematic discrepancies between human and LLM evaluations.
method Latent human preference score and linear transformations of covariates.
result Higher agreement with human ratings and exposure of systematic gaps.
Paper presents LLM-enhanced contract metadata extraction.
problem Automatic detection and annotation of legal clauses in contracts.
method Integration of publicly available and proprietary datasets with advanced LLM methodologies.
result Substantial improvements in clause identification accuracy and efficiency.
New method corrects quantization errors in LLMs using low-rank matrices.
problem Correcting quantization errors in large language models.
method Introducing low-rank weight matrices to correct quantized activations in LLMs.
result Reduces accuracy gap with original model by more than 50% using low-rank matrices.
CJE calibrates cheap LLM judges against an oracle, achieving high accuracy at a fraction of the cost.
problem Inexpensive LLM judges can produce biased rankings, leading to unreliable outcomes.
method CJE uses a small oracle to calibrate cheap scores, then evaluates at scale with valid uncertainty.
result CJE achieves 99% pairwise ranking accuracy at 14x lower cost compared to a 16x oracle/judge cost ratio.
New method uses model comparison signals to improve LLM evaluation accuracy.
problem Limited benchmark sizes and model stochasticity in evaluating LLMs' mathematical reasoning.
method Combines standard labeled outcomes with model comparison signals to design a statistically efficient evaluation framework.
result Semiparametric estimator achieves the semiparametric efficiency bound and substantially improves ranking accuracy.
This study evaluates LLMs for sentiment analysis in stock price prediction.
problem Improving stock price prediction accuracy using LLMs for news sentiment analysis.
method Compared 3 LLMs (DeBERTa, RoBERTa, FinBERT) for sentiment-driven stock prediction.
result DeBERTa outperforms other models with 75% accuracy, and ensemble model increases accuracy to 80%.
IMPACT optimizes LLM compression by focusing on activation importance, reducing model size up to 55.4%.
problem Resource constraints in deploying large language models (LLMs).
method IMPACT integrates activation importance into low-rank compression, optimizing for both size and accuracy.
result IMPACT achieves up to 55.4% greater model size reduction while maintaining comparable or better accuracy.
Improves feature selection in high-dimensional data using LLM-generated weights.
problem Inaccurate LLM-generated weights degrade feature selection performance.
method Integrates LLM-generated weights into prior inclusion probabilities using LLM Sparsity Prior (LSP).
result Improves prediction accuracy and identifies clinically relevant features.
This paper uses LLMs to generate synthetic data to improve classification accuracy in imbalanced datasets.
problem Imbalanced classification and spurious correlation in data science.
method Develops novel theoretical foundations and uses transformer models to generate synthetic data.
result Transformer models can generate high-quality synthetic data to improve classification accuracy.
LLMs can memorize economic data and recall exact values before their training cutoff.
problem Evaluating the trustworthiness of LLMs' economic forecasts during their training period.
method Demonstrated through counterfactual forecasting and analysis of LLMs' recall ability.
result LLMs have memorized economic and financial data, leading to recall-level accuracy before their knowledge cutoff.
CARROT optimizes LLM routing by choosing the cheapest and most accurate model.
problem Optimizing query routing to the most cost-effective LLM for a given task.
method CARROT uses cost and performance estimates to select the best LLM for each query.
result CARROT is minimax optimal, selecting the best LLM for any query.
LLMs struggle with financial reasoning but can outperform the market with human oversight.
problem Financial reasoning failures in LLM-generated stock market predictions.
method Evaluated four LLMs using three prompting strategies and compared to human oversight.
result LLMs require human oversight to fully realize their potential in financial markets.
The paper introduces multicalibration to improve confidence scores in LLMs.
problem Improving the reliability and interpretability of confidence scores for LLMs.
method Forming groupings of prompt/completion pairs correlated with correctness, using clustering and self-annotation. Developing multicalibration algorithms to reduce overfitting.
result Our techniques yield confidence scores that significantly improve calibration and accuracy compared to existing methods.
Intelligent financial data analysis system improves accuracy and efficiency.
problem Inefficient and inaccurate financial data analysis due to complex data and evolving contexts.
method Integrates LLMs with RAG technology for financial data analysis.
result Significant improvements in accuracy and recall (78.6% and 89.2%) compared to baseline.
LLMs outperform human analysts in predicting earnings direction.
problem Evaluating financial statements without narrative or industry-specific information.
method Trained GPT4 on standardized, anonymous financial statements and instructed to predict earnings direction.
result LLMs predict earnings directionally with accuracy comparable to narrowly trained ML models.
Improved financial sentiment analysis using LLMs with retrieval augmentation.
problem Limited performance of traditional NLP models in financial sentiment analysis.
method Retrieval-augmented Large Language Models (LLMs) with instruction tuning.
result Achieved 15% to 48% performance gain in accuracy and F1 score.
This study explores how examples influence ICL in LLMs.
problem Understanding how examples impact in-context learning in large language models.
method Theoretical study with a probabilistic model extending from Gaussian mixture model.
result The impact of pre-training knowledge and examples on ICL prediction accuracy.
FinGPT uses LLMs for real-time market sentiment analysis.
problem Real-time market sentiment analysis for trading.
method Synthesizes financial news and social media data, integrates with technical indicators, uses FinGPT for sentiment analysis.
result Generates actionable trading signals using LLMs.
MarketSenseAI uses LLMs to improve stock analysis and outperforms benchmarks.
problem Improving accuracy in stock analysis and selection.
method Combining LLMs with SEC filings, earnings calls, and macroeconomic reports.
result Significant improvement in fundamental analysis accuracy and outperformance of benchmarks.
This paper uses LLMs and cycle consistency for better machine translation evaluation.
problem Evaluating translation quality and LLM capabilities without ground truth.
method Generate translation candidates, back-translate, and evaluate cycle consistency.
result Larger LLMs or more inference passes improve cycle consistency.
This paper analyzes financial sentiment using LLMs and FinBERT, improving accuracy with few-shot examples.
problem Financial sentiment analysis for market evaluation.
method Application of large language models and FinBERT, with focus on prompt engineering and few-shot learning.
result GPT-4o achieves similar sentiment classification accuracy to FinBERT with fewer examples.
LLMs generate answers under incomplete context, and their uncertainty should scale with missing information.
problem Evaluating the quality of LLM answers under incomplete context.
method A controlled framework with varying context availability, and two uncertainty measures (sampling-based confidence and response entropy) evaluated on SQuAD.
result Response entropy increases with context removal and explains more variance in accuracy than confidence, suggesting it is a more responsive uncertainty measure.
Enhances LLMs for predicting stock movements by considering news dissemination and context.
problem Lack of consideration for news dissemination and insufficient contextual data in LLMs for stock price prediction.
method Clusters news for reach assessment, enriches prompts with specific data and instructions, fine-tunes an LLM using the dataset.
result Improves prediction accuracy by 8% compared to existing methods.
Law explains how LLMs learn to predict next tokens.
problem Understanding how LLMs process input data internally.
method Introduced a precise law governing token embeddings in LLMs.
result Each layer equally contributes to next-token prediction accuracy.
Bayesian approach quantifies uncertainty in LLM-based systems.
problem Uncertainty quantification in LLM-based systems, especially for high-stakes applications.
method Interpreting prompts as parameters in a Bayesian model, using MHLP for inference.
result Improvements in predictive accuracy and uncertainty quantification on various benchmarks.
A new framework evaluates large language models efficiently and accurately.
problem Evaluation of large language models is challenging due to stochasticity and heterogeneity of benchmarks.
method Interpretable and scalable framework based on Item Response Theory (IRT) and majorization-minimization principle.
result Our method achieves superior scalability and interpretability compared to existing approaches.
Study uses LLMs for financial sentiment analysis without fine-tuning.
problem Lack of prescriptive knowledge to leverage generative models in FSA.
method Proposes a design framework with heterogeneous LLM agents based on Minsky's theory.
result Framework yields better accuracies, especially with substantial discussions.
SLIP secures LLMs on edge devices by splitting computation and protecting sensitive parts.
problem Protecting LLMs on edge devices from theft and unauthorized use.
method SLIP uses matrix decomposition to split model computation between secure and vulnerable resources, ensuring zero accuracy degradation and minimal latency.
result SLIP is the first practical, secure hybrid protocol for protecting LLMs on edge devices.
Paper tackles source attribution for LLM-generated texts.
problem Identify the data provider of synthetic texts generated by LLMs.
method Watermarking to embed information about data providers in synthetic texts.
result Proposes and evaluates a source attribution framework that achieves effective source attribution.
Classifier detects LLM-generated text with guarantees.
problem Detecting fake LLM-generated text to prevent misuse.
method Trained classifier without auxiliary info, distinguishing human and LLM text.
result Achieves higher accuracy than existing detectors with type-I error control.
Proposes LLM-DCD for improved causal discovery from data.
problem Challenges in discovering causal relationships from observational data.
method Uses LLM to initialize DCD optimization, incorporating priors.
result Higher accuracy on benchmark datasets compared to state-of-the-art.