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…
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.
Method learns invariances in deep nets without human validation.
problem Manual selection of data augmentation parameters is cumbersome.
method Differentiable Laplace approximation for Bayesian model selection.
result Method successfully recovers invariances and improves generalization.
For assistive robots and virtual agents to achieve ubiquity, machines will need to anticipate the needs of their human counterparts. The field of Learning from Demonstration (LfD) has sought to enable machines to infer predictive models of human behavior for autonomous robot control. However, humans exhibit heterogenei…
We aim to reduce the burden of programming and deploying autonomous systems to work in concert with people in time-critical domains, such as military field operations and disaster response. Deployment plans for these operations are frequently negotiated on-the-fly by teams of human planners. A human operator then trans…
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.
TBAL reduces manual annotation but requires validated data.
problem Creating large, high-quality labeled datasets.
method Threshold-based auto-labeling using human validation data.
result Sample complexity bounds on validation data needed.
Learning the preferences of a human improves the quality of the interaction with the human. The number of queries available to learn preferences maybe limited especially when interacting with a human, and so active learning is a must. One approach to active learning is to use uncertainty sampling to decide the informat…
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…
New metrics predict human sentence comprehension across languages.
problem Predicting human sentence comprehension using computational models.
method Developed sentence-level metrics using multilingual large language models.
result Achieved high accuracy in predicting human sentence reading speeds.
Transformer models improve financial sentiment measurement.
problem Capturing nuanced sentiment from financial news articles.
method Transformer-based language models for sentiment classification and aggregation.
result Transformer models outperform traditional dictionary-based methods in sentiment classification.
New framework evaluates model explanations based on decision task improvement.
problem Evaluation of model explanations often misses practical value.
method Decision-theoretic framework quantifying three key values.
result Provides benchmarks and interprets human-AI decision support.
Proposes PA-DSL for correcting noisy human labels in automated data labeling.
problem Noisy human labels in automated data labeling.
method Uses adjudicated cases to correct noisy human labels and debias analyses.
result Maintains nominal coverage and reduces RMSE by 10-17% relative to using only adjudicated labels.
Enhances AI models with human feedback for noisy data.
problem Improving AI model alignment with human feedback in noisy environments.
method Two-stage SL+LHF framework connecting machine learning with human feedback.
result The LNCA ratio identifies conditions for SL+LHF superiority over pure SL.
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…
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 ρ-Perfect to estimate model-human correlation in subjective datasets.
problem Inherent noise in subjective ratings limits model-human correlation quantification.
method Defines ρ-Perfect as highest achievable correlation between perfect predictor and human ratings. Estimates based on heteroscedastic noise scenarios. result Demonstrates ρ-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.
LoCo-RLHF models diverse human feedback with contextual information.
problem Heterogeneous human feedback from diverse contexts and preferences.
method Low-rank contextual preference model, PRS policy.
result LoCo-RLHF achieves tighter sub-optimality gap than existing methods.
XRM discovers environments without human annotations for OOD methods.
problem Costly and biased manual annotations limit OOD methods.
method XRM trains twin networks to mimic mistakes, eliminating hyper-parameters.
result XRM achieves oracle worst-group-accuracy for OOD methods.
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.
Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its validity. Traditional measures such as confidence intervals may be insufficient…
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.
Partner-aware algorithms improve AI collaboration in multi-agent settings.
problem Improving AI cooperation in teams with shared rewards.
method Proposed Partner-Aware strategy extending Upper Confidence Bound for decentralized MAB.
result Achieves logarithmic regret in collaborative decision-making.
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.
Hölder-DPO aligns models robustly with noisy human feedback.
problem No existing alignment methods can handle severe label noise.
method Proposes Hölder-DPO, a principled alignment loss with provable redescending property.
result Hölder-DPO enables scalable human feedback valuation and improves model alignment.
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, ∼40, 20, and 9 perc…
Paper proposes a data augmentation method for LLM-generated data in market research.
problem Bias in LLM-generated data in market research.
method Statistical data augmentation approach integrating LLM-generated and real data.
result Statistically robust estimators with reduced bias and cost savings.
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.
This study proposes a framework for human-like autonomous car-following planning based on deep reinforcement learning (deep RL). Historical driving data are fed into a simulation environment where an RL agent learns from trial and error interactions based on a reward function that signals how much the agent deviates fr…
Online symptom checkers have significant potential to improve patient care, however their reliability and accuracy remain variable. We hypothesised that an artificial intelligence (AI) powered triage and diagnostic system would compare favourably with human doctors with respect to triage and diagnostic accuracy. We per…
In this paper, mm-Pose, a novel approach to detect and track human skeletons in real-time using an mmWave radar, is proposed. To the best of the authors' knowledge, this is the first method to detect >15 distinct skeletal joints using mmWave radar reflection signals. The proposed method would find several applications …
CoExBO optimizes lithium-ion batteries with user input, enhancing trust and efficiency.
problem User distrust in Bayesian optimization due to opacity and lack of user input.
method Preference learning and iterative explanation to integrate user insights.
result Algorithm converges to optimal solution even with adversarial user inputs.
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 …
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.
In this study, we propose a novel deep neural network and its supervised learning method that uses a feedforward supervisory signal. The method is inspired by the human visual system and performs human-like association-based learning without any backward error propagation. The feedforward supervisory signal that produc…
A new method for RLHF using proximal point Nash learning.
problem Capturing real human preferences in RLHF.
method Proximal point Nash learning, embedding self-play updates into a proximal point framework.
result High-probability last-iterate convergence for the combined method.