Framework for responsible LLM deployment with human involvement and decentralized technologies.
problem Challenges in deploying LLMs for high-stakes decisions, including data security and accountability.
method Interactive human involvement through multiple iterations, decentralized technologies, and automated auditing.
result Enhanced security and accountability in LLM deployment for financial decisions.
CSA fills a gap in RLVR-trained LLM deployment by providing anytime-valid selective risk control.
problem Deployment of RLVR-trained LLMs in regulated organizations requires a safety certificate for every round without waiting for long-run averages.
method CSA uses a (test statistic, validity guarantee, deployment rule) framework to fill the gap, maintaining a Ville-type e-process per threshold on a Bonferroni grid.
result CSA provides the first anytime-valid selective risk control for RLVR-trained LLMs, matching the long-run average certification rate and satisfying pathwise validity and non-refusing deployment on every cell.
Financial LLMs need explicit bias consideration to avoid invalid results.
problem Finance-specific biases inflate performance and contaminate backtests.
method Identified five recurring biases and proposed a Structural Validity Framework.
result Explicit bias consideration is necessary for valid deployment claims.
Paper fine-tunes LLMs using user edits, unifying preference, supervision, and reward feedback.
problem Adapting LLMs to user preferences and feedback types.
method Derives bounds for learning algorithms from user edits, proposes an ensembling procedure.
result Ensembling procedure outperforms individual feedback methods and robustly adapts to different user-edit distributions.
Simple online monitor detects unsafe LLM outputs.
problem LLMs generate unsafe outputs despite training.
method Thresholding external verifier signal to decide alarms.
result Simple design competitive with advanced methods.
LLMs cause inconsistent financial outputs, smaller models are more reliable.
problem Inconsistent outputs from LLMs undermine auditability and trust in financial workflows.
method Finance-calibrated deterministic test harness, task-specific invariant checking, model classification, and cross-provider validation.
result Smaller models (Granite-3-8B, Qwen2.5-7B) achieve 100% output consistency, while larger models like GPT-OSS-120B have high drift.
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.
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.
LLMs can collude in market divisions, maximizing profits.
problem Strategic collusion of LLM agents in multi-commodity markets.
method Examined LLMs in Cournot competition frameworks, analyzing pricing and resource allocation strategies.
result LLMs can monopolize specific commodities without direct human input or explicit collusion commands.
The paper introduces Relative Bias to quantify LLM bias systematically.
problem Quantifying bias in LLMs is challenging due to ambiguity and rapid model emergence.
method Relative Bias framework using Embedding Transformation and LLM-as-a-Judge methodologies.
result The two scoring methods show strong alignment, providing a systematic approach.
A new framework evaluates LLM calibration in open-ended QA.
problem Evaluating LLM calibration in open-ended QA settings.
method Sem-ECE framework: sampling answers, grouping by semantic classes, and using frequencies as confidence.
result Sem-ECE estimators are unbiased and Sem2 achieves smaller calibration error. Develops a power-calibrated framework for LLM watermarking, optimizing tradeoffs between detectability and distortion.
problem The trade-off between detectability and semantic distortion in logit-based watermarking.
method Power-calibrated statistical framework for watermark hyperparameters, establishing explicit relationships.
result Derives practical parameter selection procedures achieving optimal tradeoffs under constraints.
PredictaBoard benchmarks LLM score predictors to assess their ability to anticipate errors.
problem Inconsistent performance of LLMs in common sense reasoning tasks.
method Collaborative benchmarking framework evaluating pairs of LLMs and assessors using rejection rate at different tolerance errors.
result Highlights the need to evaluate predictability alongside performance for safer AI systems.
Look-Ahead-Bench evaluates financial LLMs for lookahead bias, revealing significant differences in model performance.
problem Measuring and mitigating lookahead bias in financial LLMs.
method Standardized benchmark evaluating model behavior in practical financial scenarios, analyzing performance decay across market regimes.
result Standard LLMs exhibit significant lookahead bias, while Pitinf models show improved generalization and reasoning abilities.
Optimal query allocation improves extractive QA efficiency with LLMs.
problem Efficiency and reliability in extractive question answering with LLMs.
method Learning-to-Defer framework that allocates queries to specialized models.
result Enhanced answer reliability with reduced computational overhead.
PandaAI: A practical agent for neuro-symbolic data analysis and decision-making in finance
problem Sequential decision-making in finance
method Leveraging LLMs for market regime modeling and constrained alpha generation
result PandaAI achieves higher Rank IC and lower maximum drawdown
Efficiently estimates uncertainty for LLM-based entity linking in tabular data.
problem Accurate and reliable uncertainty estimates for LLM-based entity linking in tabular data.
method Self-supervised approach using token-level features for single-shot inference.
result Effective uncertainty estimates detected at a fraction of computational cost.
Proposes a method to choose thresholds for LLM evaluation metrics.
problem Ensuring reliable large language models (LLMs) with correct threshold selection.
method Identify risks, stakeholders' risk tolerance, and use ground-truth data to determine thresholds.
result Demonstrates a concrete example with the Faithfulness metric and HaluBench dataset.
Paper explores using LLMs for zero-shot reinforcement learning in continuous spaces.
problem Leveraging LLMs for continuous state spaces in reinforcement learning.
method Disentangled In-Context Learning (DICL) to handle multivariate data and control signal.
result DICL produces well-calibrated uncertainty estimates in reinforcement learning settings.
LMoE uses LLMs to improve stock trading by selecting experts based on textual and price data.
problem Traditional neural network-based router selection in MoE models is suboptimal and ignores textual data.
method Proposes LLMoE, using LLMs as routers to select experts based on historical price data and stock news.
result LLoM outperforms state-of-the-art MoE models and other deep neural network approaches.
Paper reviews the evolution of alpha from human insight to AI-powered systems.
problem Exceeding market benchmarks in finance.
method Five-stage taxonomy integrating representation learning, multimodal data fusion, and LLM agents.
result Unified framework for evaluating and developing next-gen alpha systems.
Study finds uncertainty estimators weakly correlate with LLM hallucinations.
problem Characterizing the relationship between uncertainty estimators and LLM hallucinations.
method Systematic empirical study of diverse uncertainty estimators across hallucination types and benchmarks.
result Uncertainty estimators weakly correlate with LLM hallucinations, depending on hallucination type and LLM.
New framework assesses LLM security risks in BFSI.
problem Lack of domain-specific security evaluation for LLMs in BFSI.
method Risk-aware evaluation framework combining taxonomy, automated red-teaming, and ensemble judging.
result Higher decoding stochasticity and adaptive interaction lead to more severe disclosures.
RLVR maintains safety while improving reasoning capabilities in LLMs.
problem Safety-capability tradeoff in fine-tuning LLMs.
method Reinforcement Learning with Verifiable Rewards (RLVR) and theoretical analysis.
result RLVR can enhance reasoning while maintaining safety guardrails.
FinRL-X unifies trading components for AI and rule-based strategies.
problem Inconsistent between research and live deployment in trading platforms.
method Modular architecture integrating data processing, strategy construction, backtesting, and execution.
result Unified protocol supports AI and rule-based trading components without altering execution.
New method certifies risks of LLM outputs, improving accuracy and reliability.
problem Uncertain and incorrect outputs from large language models.
method Information-lift certificates using PAC-Bayes bounds and skeleton design.
result Achieves 77.0% coverage at 2% risk, outperforming baselines.
SIREN protocol corrects optimistic winner's scores in LLM evaluation.
problem Optimistic winner's scores in LLM evaluation due to adaptive benchmarking.
method SIREN protocol that freezes post-search shortlist, separates selection and evaluation, and uses bootstrap for uncertainty quantification.
result SIREN provides valid confidence intervals for procedure-performance curves and deployment conclusions.
Bayesian principles improve agentic AI decision-making.
problem Decision-making under uncertainty in agentic AI systems.
method Bayesian decision theory applied to the orchestration layer of agentic AI.
result Bayesian principles enhance agentic AI's ability to make decisions under uncertainty.
ABC improves uncertainty quantification in LLMs for clinical diagnostics.
problem Overconfident and poorly calibrated estimates of LLMs in clinical domains.
method Approximate Bayesian Computation (ABC) for likelihood-free inference.
result Improves accuracy by up to 46.9%, reduces Brier scores by 74.4%, and enhances calibration.
Train a lightweight carry-on model on existing LLMs for faster customization.
problem Customizing large language models for specific tasks is computationally expensive.
method Train an additional branch of transformer blocks on the final-layer embedding of pretrained LLMs, then merge them with a carry-on module.
result Training a 100M carry-on layer requires less than 1GB GPU memory, making it scalable and affordable.
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.
Holographic Invariant Storage uses vector architectures to ensure LLM safety at design time.
problem Mitigating context drift in large language models (LLMs) during deployment.
method Introduces Holographic Invariant Storage (HIS) protocol that combines known properties of bipolar Vector Symbolic Architectures into a design-time safety contract.
result Closed-form guarantees for single-signal recovery fidelity, continuous-noise robustness, and multi-signal capacity degradation are provided and validated.
Proposes a new algorithm for efficient online model selection of LLMs considering the increasing-then-converging trend.
problem Balancing cost and performance in choosing the best LLM among a diverse set of models.
method Introduces a time-increasing bandit algorithm (TI-UCB) that predicts model performance increases and balances exploration and exploitation.
result Achieves a logarithmic regret upper bound, indicating a fast convergence rate in model selection.
Direct Density Ratio Optimization aligns LLMs with human preferences without assuming specific models.
problem Statistical inconsistency in aligning LLMs with human preferences.
method Direct Density Ratio Optimization (DDRO) estimates density ratio directly.
result DDRO is statistically consistent, converging to true human preferences as data grows.
Geometric stability predicts steerability and detects drift in language models.
problem Predicting steerability and detecting drift in language models.
method Supervised and unsupervised geometric stability measures.
result Supervised geometric stability predicts steerability with high accuracy and detects drift earlier.
ValueBlindBench tests LLM-generated investment rationales for validity before returns are known.
problem Delayed-ground-truth evaluation of LLM-generated investment rationales.
method Agreement-gated stress testing protocol to validate LLM-judged rationales.
result ValueBlindBench prevents overclaims and identifies flawed financial constructs.
Proposes integrating global and local entropy for more reliable LLMs.
problem Uncertainty in large language models (LLMs) leads to unreliable predictions.
method Measures global uncertainty from hidden-state matrices and local uncertainty from tokens, combining them via a multiplicative gate.
result Global-Local Uncertainty (GLU) outperforms unsupervised baselines across multiple models and benchmarks.
New method calibrates LLMs for safety-critical tasks with scalable Bayesian inference.
problem Overconfidence in LLMs after fine-tuning for specific tasks.
method Orthogonalized Low-Rank Adapters (PoLAR) with variational Bayesian inference.
result Scalable and well-calibrated uncertainty estimation for LLMs.
FLoE adapts LLMs by selectively deploying LoRA adapters based on layer importance and task requirements.
problem Uniform LoRA deployment across all layers leads to inefficient and redundant parameter allocation.
method FLoE uses Fisher information to dynamically identify task-critical layers and optimizes LoRA ranks.
result FLoE achieves significant efficiency-accuracy trade-offs, especially in resource-constrained environments.
Survey examines distillation methods for large language models.
problem Efficiently compress large language models while preserving their capabilities.
method Knowledge Distillation and Dataset Distillation techniques.
result Integrating KD and DD can produce more effective and scalable compression strategies.
Study detects and explains positional bias in financial LLMs.
problem Positional bias in financial decision-making using LLMs.
method Unified framework and benchmark for detecting and quantifying bias in Qwen2.5 models.
result Positional bias is pervasive, scale-sensitive, and resurfaces under nuanced prompt designs.
QuantEase optimizes LLMs with CD-based quantization, achieving state-of-the-art performance.
problem Efficiently quantize large language models for deployment.
method Layer-wise quantization using CD-based algorithms with matrix and vector operations.
result State-of-the-art performance in perplexity and zero-shot accuracy.
Work shows hallucination detection by LLMs is impossible without expert feedback.
problem Detecting hallucinations in LLMs is theoretically impossible without expert-labeled feedback.
method Investigated hallucination detection using a theoretical framework inspired by language identification.
result Automated hallucination detection is impossible for most language collections without expert-labeled feedback.
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.
Enhances LLM quantization with MDBF, improving perplexity and accuracy.
problem Limited performance of Double Binary Factorization in extreme quantization.
method Introduces Multi-envelope DBF, retaining sign matrices and replacing single envelope with rank-l envelope. result Improves perplexity and zero-shot accuracy over previous binary formats.
New scaling laws optimize model size, training, and inference for better performance.
problem Trade-off between model size and inference cost in modern LLMs.
method Train-to-Test (T2) scaling laws that jointly optimize model size, training tokens, and inference samples. result Optimal pretraining decisions shift into overtraining regime, leading to stronger performance.
TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.
problem Efficient deployment of large language models constrained by static parameter footprint.
method Structured Trapezoidal ExpertNeuron Pruning (TENP) identifies and retains important experts and neurons.
result DeepSeek model achieves 10% better performance on code generation tasks with 40% expert sparsity.
FUSE improves verification quality without ground truth labels.
problem Verification of model outputs using imperfect judges and reward models.
method Ensembling verifiers without ground truth labels using spectral algorithms.
result FUSE matches or improves upon semi-supervised alternatives in test-time scaling experiments.