AI assistants often give convincing but incorrect responses to match user beliefs.
problem Sycophancy in AI assistants that use human feedback.
method Examined five AI assistants across four tasks, analyzed human preference data, and compared model outputs against preference models.
result Sycophancy is a general behavior of AI assistants, driven in part by human preference judgments.
AI-assisted interviews allow respondents to describe experiences naturally, but mapping those accounts into structured survey variables is fallible.
problem Mapping AI-assisted interview responses into structured survey variables is fallible.
method Adaptive Matrix Validation (AMV) is proposed, which involves mapping responses into tabular data and using a small set of structured questions for statistical adjustment.
result The estimator calibrates mapped values using validation answers from other respondents and corrects remaining error with validation answers observed for the target respondent.
Generative AI boosts productivity and improves customer service quality.
problem Productivity and quality of customer support agents.
method Staggered introduction of a generative AI-based conversational assistant in customer support.
result AI increases productivity by 15% on average, with significant heterogeneity across workers.
New AI assistant for power grid operators simplifies complex decision-making.
problem Complexity and uncertainty in power grid operations.
method Unified human-machine interface and AI integration.
result Development of a new assistant framework for power grid operators.
The paper addresses the difficulty of decision makers trusting AI-assisted predictions and proposes a method to improve confidence values.
problem Decision makers struggle to trust AI-assisted predictions based on confidence values.
method The paper investigates why decision makers have difficulties and proposes a method to construct more useful confidence values.
result Multicalibration with respect to the decision maker's confidence on her own predictions is a sufficient condition for alignment, leading to better decisions.
Optimal allocation of human effort to correct AI assessments in decision-making.
problem How to allocate costly human effort to correct noisy or biased AI-generated assessments.
method Decision-theoretic framework treating AI assessments as signals and human judgments as costly information. Developed estimation procedures under nonparametric and linear models.
result Our approach substantially outperforms LLM-only predictions and achieves performance comparable to full human review while using only 20-30% of the human information.
A new framework uses text descriptions to improve protein design.
problem Lack of effective methods to incorporate textual descriptions in protein design.
method ProteinDT framework that combines text and protein structural information.
result ProteinDT significantly improves protein design accuracy and performance.
New method improves active statistical inference by reducing noise.
problem Inaccurate uncertainty estimates in active sampling lead to noisy results.
method Robust sampling strategies that interpolate between uniform and active sampling based on uncertainty scores.
result The robust sampling ensures that the estimator is never worse than uniform sampling and usually outperforms active inference.
The paper studies how to allocate human validation in AI-assisted tasks to minimize errors.
problem Heterogeneous reliability of AI-generated signals across tasks, products, and customer segments.
method Tuned prediction-powered inference, upper confidence bounds policy, Neyman square-root rule.
result The proposed policy outperforms uniform and epsilon-greedy allocation, closing most of the gap to the oracle when reliability is heterogeneous.
Note on subgaussian bounds for sign-quantized linear maps.
problem Understanding subgaussian behavior of sign-quantized linear maps.
method Developed a dimension-independent subgaussian concentration bound for Gaussian vectors under nonlinear mappings.
result Answered a question about sign-quantized linear maps using a new subgaussian bound.
TacticAI helps football coaches improve tactics by analyzing corner kicks.
problem Developing effective responses to rival teams' tactics algorithmically.
method TacticAI combines predictive and generative components to suggest player setups and position adjustments.
result TacticAI's model suggestions are favored over existing tactics 90% of the time by football domain experts.
AI-assisted framework detects and predicts rare extreme events.
problem Detecting rare extreme events in complex systems.
method Combining BED with DNOs for active learning and forecasting.
result Framework outperforms GPs and uncovers extremes without initial data.
Machine learning and AI-assisted trading have attracted growing interest for the past few years. Here, we use this approach to test the hypothesis that the inefficiency of the cryptocurrency market can be exploited to generate abnormal profits. We analyse daily data for 1,681 cryptocurrencies for the period between N…
EduQG generates better educational questions by pre-training on scientific text.
problem Improving the quality of educational questions for scalable self-assessment.
method Adapting a large language model for educational question generation, pre-trained on scientific text.
result EduQG produces superior educational questions compared to baseline models.
Generative AI boosts analyst reports but increases forecast errors.
problem Improving financial analyst reports with AI.
method Natural experiment using FactSet's AI platform.
result AI-assisted reports are more comprehensive but lead to higher forecast errors.
New arithmetic phenomenon 'murmurations' detected using AI.
problem Detecting new arithmetic patterns in large datasets.
method Machine learning interpretability tools (PCA, saliency, convolutional filters).
result Murmurations encode Frobenius traces and connect to number theory.
Framework enhances AI explainability by aligning with human cognitive models.
problem Lack of explainability in AI models hinders trust and accountability.
method Integrates explainability techniques with Malle's five category model of behavior explanation.
result Demonstrates practical relevance in credit risk assessment and regulatory analysis.
AI-assisted heart disease diagnosis reduces misdiagnosis and saves lives.
problem Misdiagnosis of heart disease leads to unnecessary deaths.
method Developed an AI application using ML and DNN algorithms on a dataset from the Cleveland Clinic Foundation.
result DNN model achieved a 92% accuracy rate, reducing misdiagnosis.
AI helps build particle physics theories more efficiently.
problem Building viable particle physics theories requires extensive effort and intuition.
method Developed AMBer, a reinforcement learning framework interacting with physics software.
result AMBer constructs viable models with fewer parameters, validating in neutrino theories.
Designing AI market for content creation
problem Balancing technological progress and individual incentives for content creation
method Dynamic Stackelberg game model
result Inducing greater reliance on AI-assisted creation
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.
AI helps simplify complex ship finance processes.
problem Complexity in ship finance due to data and regulatory requirements.
method Integrates large language models for document comprehension, information extraction, and workflow automation.
result AI-assisted systems can support maritime finance professionals in managing complex information and reporting requirements.
AI uses language models to find instrumental variables quickly.
problem Finding valid instrumental variables is a challenging and heuristic process.
method Uses large language models to search for new instrumental variables through narratives and counterfactual reasoning.
result Demonstrates the effectiveness of multi-step and role-playing prompting strategies for LLMs.
FST.ai 2.0 improves Taekwondo decision-making with AI, reducing review time and increasing trust.
problem Fair, transparent, and explainable decision-making in Taekwondo.
method Pose-based action recognition, epistemic uncertainty modeling, interactive dashboards.
result 85% reduction in decision review time, 93% referee trust in AI-assisted decisions.
AI task delegation faces incentive collapse with unbounded payments as AI accuracy rises.
problem Incentive collapse in AI-assisted task delegation schemes.
method General impossibility result and sentinel-auditing payment mechanism.
result Sentinel-auditing mechanism enforces positive human effort at finite cost, independent of AI 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.
Fairness in LLMs is impossible due to inherent technical challenges.
problem Ensuring fairness in large language models (LLMs) with rigorous definitions.
method Analysis of various technical fairness frameworks.
result No feasible technical fairness frameworks for LLMs due to large amounts of unstructured data and many potential combinations.
LR-Robot automates SLRs with AI, expert oversight, and multidimensional analysis.
problem Efficient but contextually limited outputs from existing SLR frameworks.
method Human-in-the-loop process, structured knowledge sources, retrieval-augmented generation.
result Empirical demonstration of AI-driven literature synthesis in option pricing.
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.
RLFA estimates misstated monetary fraction with weighted sampling without replacement.
problem Estimating misstated monetary fraction with given accuracy and confidence.
method Developed new confidence sequences for weighted average of unknown values using randomized weighted sampling and side information.
result Adaptive methods improve accuracy of estimates based on side information's predictive power.
AI enhances personalized drug development and decision-making in pharma.
problem Traditional drug development lacks personalized treatment plans.
method Application of AI in drug discovery, clinical trials, and post-marketing assessment.
result AI improves personalized medicine, optimizing health outcomes.
The paper uses AI to analyze on-chain parameters and identify risky cryptocurrencies.
problem Identifying risky cryptocurrencies and understanding their price factors.
method Historical data analysis, AI algorithms, clustering, classification.
result A significant negative correlation between cryptocurrency price and maximum and total supply, and a weak positive correlation with 24-hour trading volume.
LR-Robot accelerates SLRs by combining expert oversight and AI, revealing trends and patterns in financial research.
problem Manual SLRs are impractical due to the scale and complexity of modern financial research.
method Domain experts define taxonomies and constraints, LLMs execute classification, and human evaluation ensures reliability.
result AI can understand and synthesize literature, revealing trends and core research directions.
Proposes BGNN for tumor heterogeneity prediction using graph neural networks.
problem Tumor classification limitations and heterogeneity assessment challenges.
method Artificial data generation, tumor heterogeneity estimation, and BGNN model development.
result BGNN achieves 89.67% accuracy in predicting tumor heterogeneity. AI models failed to profitably predict cryptocurrency extrema on Binance Spot.
problem Tackling the profitability of candle-based machine learning models for short-term cryptocurrency trading.
method Scripted fixed-seed model runs and deterministic simulators with human supervision.
result Strongest evidence found negative, with models underperforming buy-and-hold strategies.
This paper presents a method to generate synthetic data with differential privacy to protect user privacy while maintaining data trends.
problem Protecting user privacy while using real data for AI applications.
method Develops a practical guide to generating synthetic data using differential privacy.
result Synthetic data can be generated to preserve trends of real data while ensuring strong privacy protections.