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

71142213284 · Jun 202019922001200920172026
48 results for human validation

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.

K-fold Cross Validation is commonly used to evaluate classifiers and tune their hyperparameters. However, it assumes that data points are Independent and Identically Distributed (i.i.d.) so that samples used in the training and test sets can be selected randomly and uniformly. In Human Activity Recognition datasets, we…

2019-04-04abs ↗pdf ↗

Digital personas improve survey results for stable attributes but fail for subjective responses.

problem When can digital personas reliably approximate human survey findings?
method Using LISS panel, constructed personas from background variables and survey histories, tested against held-out post-cutoff answers.
result Digital personas improve alignment with human response distributions for stable attributes but fail for subjective responses.

Efficient method for training deep learning models with human validation and statistical analysis.

problem Challenges in labeling medical images for deep learning, including time and cost.
method Four-step method using automated data and human visual checks for iterative refinement and statistical validation.
result Initial model accuracy improved from 92% to 98% with statistical validation.

Study causal effects on humans in mixed human-AI systems with unobserved unit types.

problem Estimating causal effects on humans in systems with unobserved unit types and interaction networks.
method Assumed human-AI prior, causal message passing (CMP) framework, subpopulation analysis.
result Consistently recover human-specific causal effects using subpopulations with varying expected human composition and treatment exposure.

Study reveals LLM personality patterns but lacks behavioral consistency.

problem Understanding and validating personality traits in LLMs.
method Characterized LLM personality across three dimensions: training dynamics, self-report validity, and intervention effects.
result Self-reported traits do not reliably predict behavior, and instructional alignment affects trait expression but not behavior.

RLHF fails when humans only partially observe, leading to inflated or overjustified feedback.

problem Failure of reinforcement learning from human feedback in partially observable environments.
method Formal definition of failure cases, modeling human as Boltzmann rational, analyzing information provided by feedback.
result RLHF can deceptively inflate or overjustify feedback when humans have partial observations.

New method for valid and exact statistical inference of multi-dimensional change-points.

problem Statistical inference of change-points in multi-dimensional sequences.
method Proposes a method to guarantee the statistical reliability of both location and components of detected changes.
result Demonstrates the effectiveness of the method in genomic abnormality identification and human behavior analysis.

MCAL reduces labeling costs by 6x for auto-labeling data sets.

problem Expensive human annotation for ground-truth data sets.
method Iterative approach that trains a classifier to auto-label part of the data set, determining which samples to label using humans and which to label using the classifier at each step.
result 6x lower overall cost compared to human labeling the entire data set, always cheaper than competing strategies.

Humans are spectacular reinforcement learners, constantly learning from and adjusting to experience and feedback. Unfortunately, this doesn't necessarily mean humans are fast learners. When tasks are challenging, learning can become unacceptably slow. Fortunately, humans do not have to learn tabula rasa, and learning s…

2020-02-25abs ↗pdf ↗

Deep learning has enabled traditional reinforcement learning methods to deal with high-dimensional problems. However, one of the disadvantages of deep reinforcement learning methods is the limited exploration capacity of learning agents. In this paper, we introduce an approach that integrates human strategies to increa…

2018-06-12abs ↗pdf ↗

Generative Augmented Inference improves AI-generated data for causal inference.

problem Challenges in using AI-generated annotations for reliable causal inference.
method Generative Augmented Inference (GAI) treats AI outputs as informative features for learning true labels, flexibly modeling the relationship using nonparametric methods.
result GAI significantly reduces estimation error and improves confidence interval quality compared to human-only and PPI-based methods.

Paper introduces ρρ-Perfect to estimate model-human correlation in subjective datasets.

problem Inherent noise in subjective ratings limits model-human correlation quantification.
method Defines ρρ-Perfect as highest achievable correlation between perfect predictor and human ratings. Estimates based on heteroscedastic noise scenarios.
result Demonstrates ρρ-Perfect can distinguish model limitations from data quality issues.

Paper proposes a robust RLHF algorithm for LLMs, improving response preference over baselines.

problem Reward model misspecifications in RLHF for LLMs.
method Proposes a robust algorithm to reduce reward and policy estimator variance, theoretically and empirically validated.
result Consistently outperforms existing methods on LLM benchmark datasets, favoring 77-81% of responses over baselines.

Human stablecoin transactions predict political risk in cryptocurrency markets.

problem Predicting political risk in cryptocurrency markets.
method Structural break analysis and surrogate-based robustness tests.
result Human-driven stablecoin transactions shift significantly before major political events.

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.

IAL uses interactive learning to improve model performance with minimal human feedback.

problem Overfitting and high human interaction cost in training neural networks.
method IAL framework with NAP attention generator and reranking algorithm.
result IAL significantly outperforms baselines with less retraining and human interaction.

Language-based methods improve human similarity approximations without requiring many human judgments.

problem Approximating human similarity judgments using pre-trained deep neural networks (DNNs) is challenging and expensive.
method Developed language-based methods to approximate human similarity judgments, validated with adaptive tag collection pipeline.
result Language-based methods significantly improve performance over DNN-based methods with fewer human judgments.

Method tackles uncertainty in reward models for LLMs from heterogeneous human feedback.

problem Uncertainty in reward models for LLMs from heterogeneous human feedback.
method Heterogeneous preference framework and alternating gradient descent algorithm.
result Established theoretical guarantees for estimator convergence and asymptotic distribution.

The paper tackles learning from imperfect human feedback, especially in dueling bandit problems.

problem Learning from human feedback that can be irrational or imperfect.
method Developed a Robustified Stochastic Mirror Descent for Imperfect Dueling (RoSMID) algorithm.
result Achieved nearly optimal regret for dueling bandit problems under imperfect human feedback.

We construct genomic predictors for heritable and extremely complex human quantitative traits (height, heel bone density, and educational attainment) using modern methods in high dimensional statistics (i.e., machine learning). Replication tests show that these predictors capture, respectively, \sim40, 20, and 9 perc…

2017-09-19abs ↗pdf ↗

This paper proposes a method to use LLMs as auxiliary evaluators in place of human judges.

problem The need for cost-effective and scalable evaluation of AI systems.
method Formulates a two-stage sampling design with LLM evaluations and human ratings, using a doubly robust estimator.
result Proposes a method to determine optimal sample sizes for human and LLM ratings.

Classifying chemicals according to putative modes of action (MOAs) is of paramount importance in the context of risk assessment. However, current methods are only able to handle a very small proportion of the existing chemicals. We address this issue by proposing an integrative deep learning architecture that learns a …

2018-11-21abs ↗pdf ↗

Detects AI-synthesized speech using cepstral and bispectral analysis.

problem Validating the authenticity of speech from AI-generated content.
method Integrates cepstral and bispectral analysis for distinguishing human from AI-synthesized speech.
result Higher-order statistics show less correlation for human speech compared to AI-synthesis, and cepstral analysis reveals unique power components.

Framework for multi-agent RL with human feedback in a Snake game.

problem Improving multi-agent reinforcement learning with human feedback.
method Developed a simulated game environment for offline model training and online competitions. Introduced HILL methods and reward manipulation heuristics.
result Agents with HILL methods outperform those without in online competitions.

Paper develops methods to optimize policies directly from human feedback without reward inference.

problem Challenges in RLHF, including reward model overfitting and distribution shift.
method Develops two algorithms for RLHF without reward inference, using zeroth-order gradient approximators.
result Establishes polynomial convergence rates and outperforms existing methods in numerical experiments.