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.

168,695 papers · 148 categories

Trend · papers per month

306089119 · Oct 201919922001200920172026
48 results for human sub-rationality

Study models human investors' sub-rational behavior in financial markets.

problem Lack of a comprehensive model for human sub-rationality in financial markets.
method Flexible reinforcement learning model incorporating five human sub-rational aspects.
result Model accurately reproduces human behavior and reveals insights into market dynamics.

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.

When machine predictors can achieve higher performance than the human decision-makers they support, improving the performance of human decision-makers is often conflated with improving machine accuracy. Here we propose a framework to directly support human decision-making, in which the role of machines is to reframe pr…

2019-05-29abs ↗pdf ↗

Conformal prediction sets improve human decision making by quantifying model uncertainty.

problem Humans signal uncertainty and offer alternatives when unsure, but machine learning models often lack this feature.
method Conducted a randomized controlled trial with human subjects given conformal prediction sets.
result Human accuracy improves when given conformal prediction sets compared to fixed-size prediction sets.

This paper argues for more realistic human models in RL.

problem Current RL models oversimplify human feedback, ignoring personal, contextual, and dynamic aspects.
method Calls for interdisciplinary research on human feedback in RL.
result Realistic human models are needed for robust human-in-the-loop RL systems.

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to them can converge to coordination protocols that fail to understand and be unders…

2019-10-13abs ↗pdf ↗

This work advances collaborative decision making by combining human and AI strengths in uncertainty quantification.

problem Current AI lacks robust decision-making capabilities under uncertainty, especially in high-stakes contexts.
method Introduces Human AI Collaborative Uncertainty Quantification (HACUQ) framework, formalizing AI-human collaboration and developing calibration algorithms.
result Optimal collaborative prediction sets follow a two-threshold structure, and online adaptation algorithms can adapt to evolving human behavior.

Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and automatically calibrated complexity. However, automating human expertise remains elusive; for example, Gaussian processes with standard kerne…

2015-10-26abs ↗pdf ↗

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.

Combines human and model predictions for improved accuracy.

problem Improving classification accuracy when both human and model predictions are imperfect.
method Uses confusion matrices and calibration to combine probabilistic model outputs with human class-level predictions.
result Human-model combinations consistently outperform either alone, with accuracy gains even with limited human input.

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.

Generative classifiers show surprising human-like performance.

problem Comparing generative and discriminative models for object recognition.
method Built on recent advances in generative modeling to create classifiers and compared them to discriminative models.
result Generative classifiers outperform discriminative models in several key areas, including shape bias and out-of-distribution accuracy.

Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and interpreting inputs from humans. In contrast, inputs created by humans are often treated as a given. We investigate how inputs of humans can…

2019-12-08abs ↗pdf ↗

IDT learns human preferences from uncertain decisions, even when humans are suboptimal.

problem Learning human preferences from uncertain and suboptimal decisions.
method Inverse decision theory (IDT) framework, statistical analysis of IDT, characterizing sample complexity.
result Learning preferences is easier when decisions are more uncertain, even if humans are suboptimal.

Learning preferences implicit in the choices humans make is a well studied problem in both economics and computer science. However, most work makes the assumption that humans are acting (noisily) optimally with respect to their preferences. Such approaches can fail when people are themselves learning about what they wa…

2019-01-24abs ↗pdf ↗

Autonomous systems can substantially enhance a human's efficiency and effectiveness in complex environments. Machines, however, are often unable to observe the preferences of the humans that they serve. Despite the fact that the human's and machine's objectives are aligned, asymmetric information, along with heterogene…

2017-05-26abs ↗pdf ↗

This work compares human feedback methods for reward learning in bandits.

problem Understanding how human feedback affects the performance of reward learning methods.
method Theoretical comparison of human feedback approaches in offline contextual bandits.
result Human bias and uncertainty in feedback modeling impact the theoretical guarantees of reward learning methods.

We present a novel human-aware navigation approach, where the robot learns to mimic humans to navigate safely in crowds. The presented model, referred to as DeepMoTIon, is trained with pedestrian surveillance data to predict human velocity in the environment. The robot processes LiDAR scans via the trained network to n…

2018-03-09abs ↗pdf ↗

Deep RL mimics human driving for collision avoidance in self-driving cars.

problem Developing human-like driving policies for autonomous vehicles in mixed traffic environments.
method Model-free, deep reinforcement learning approach using a combination of rule-based and expert-driven data.
result Demonstrated human-like driving policies through Gaussian process modeling of track position and speed distributions.

Develops a statistical framework to measure uncertainty in model rankings based on human preferences.

problem Uncertainty in model rankings based on human preferences due to mismatch between human and model preferences.
method Statistical framework using pairwise comparisons by humans and models to provide rank-sets for each model.
result Rank-sets constructed using only pairwise comparisons by strong models often do not cover the true ranking of human preferences.

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.

Large-scale public datasets have been shown to benefit research in multiple areas of modern artificial intelligence. For decision-making research that requires human data, high-quality datasets serve as important benchmarks to facilitate the development of new methods by providing a common reproducible standard. Many h…

2019-03-15abs ↗pdf ↗

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 approach to algorithmic fairness for human-AI collaboration considers compliance with human decisions.

problem Current fairness approaches assume perfect human compliance, but real-world compliance is often poor.
method Defines compliance-robustly fair algorithms and proposes an optimization strategy to improve fairness.
result Algorithmic recommendations can improve fairness even if humans do not fully comply with fair algorithms.

PILAF optimizes reward models from human feedback for better policy alignment.

problem Creating accurate reward models from human feedback for policy optimization.
method Policy-Interpolated Learning for Aligned Feedback (PILAF) that explicitly aligns preference learning with maximizing underlying oracle reward.
result PILAF is optimal from both optimization and statistical perspectives, demonstrating strong performance in RLHF settings.

Generative models have made immense progress in recent years, particularly in their ability to generate high quality images. However, that quality has been difficult to evaluate rigorously, with evaluation dominated by heuristic approaches that do not correlate well with human judgment, such as the Inception Score and …

2019-11-30abs ↗pdf ↗

Quriosity analyzes curiosity-driven questions from diverse sources.

problem Understanding and analyzing human curiosity-driven questions.
method Collection of 13.5K questions from various sources, development of an iterative prompt improvement framework.
result 42% of questions are causal, revealing unique linguistic properties.

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.

TraLFM models human mobility patterns from traffic trajectories.

problem Understanding human mobility patterns from traffic data.
method Latent factor modeling of sequential, personal, and temporal factors.
result TraLFM significantly outperforms state-of-the-art methods in latent factor analysis and next location prediction.

Human decision-making underlies all economic behavior. For the past four decades, human decision-making under uncertainty has continued to be explained by theoretical models based on prospect theory, a framework that was awarded the Nobel Prize in Economic Sciences. However, theoretical models of this kind have develop…

2019-05-22abs ↗pdf ↗

Paper tackles RLHF with DCPPO method, proving near-optimal suboptimality.

problem Challenges in offline RLHF with limited human feedback and bounded rationality.
method DCPPO method involving three stages: MLE, reward function recovery, and pessimistic value iteration.
result DCPPO's suboptimality almost matches classical pessimistic offline RL in terms of distribution shift and dimension.