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…
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.
168,982 papers · 148 categories
Trend · papers per month
48 results for “human assistance”
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.
Machine learning automates proof generation in Coq proof assistant.
problem Automating proof construction in proof assistants.
method Developed ASTactic, a deep learning model generating tactics as ASTs.
result ASTactic can generate effective tactics and prove new theorems.
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.
Designs algorithms to assist humans without affecting their decisions.
problem Algorithms often fail to improve human decisions.
method Formalizes algorithm design using potential outcomes framework and monotonicity assumption.
result Derives minimax optimal recommendation algorithms for limited data.
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.
Paper tackles regression under human assistance, showing NP-hardness and developing a greedy algorithm.
problem Optimizing machine learning models under human intervention.
method Introduced ridge regression under human assistance, derived NP-hardness, and developed a greedy algorithm.
result Greedy algorithm achieves good performance in medical diagnosis and content moderation applications.
Study shows human advisors use context to improve student outcomes in algorithm-assisted advising.
problem How human advisors use context to guide interventions in algorithm-assisted advising.
method Mixed-methods approach combining quantitative and qualitative data from a randomized controlled trial.
result 2 out of 3 interventions by advisors were plausibly 'expertly targeted' to students using non-algorithmic context.
New research shows machine-assisted decisions can still be unfair even when the algorithm is fair.
problem Ensuring fairness in decisions made with machine-assisted human input.
method Formal model and lab experiment to analyze how machine predictions affect human decisions.
result Excluding information about protected groups from machine predictions can increase disparities.
Humans are the final decision makers in critical tasks that involve ethical and legal concerns, ranging from recidivism prediction, to medical diagnosis, to fighting against fake news. Although machine learning models can sometimes achieve impressive performance in these tasks, these tasks are not amenable to full auto…
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.
Framework allows organizations to collaborate on learning tasks securely.
problem Limited collaboration due to security constraints.
method Assisted Learning framework for supervised learning tasks.
result Near-oracle learning performance achieved without revealing sensitive information.
Improved accuracy in a commercial assistant by smartly selecting new training data.
problem Expensive and time-consuming to annotate new data for ML systems.
method Automatically identifies new helpful examples suitable for human annotation.
result The proposed method leads to higher accuracy improvements with a fixed annotation budget.
LFD method improves text classification by making features clearer and less label-leaking.
problem Creating interpretable text representations that are both predictive and understandable.
method LFD method: proposes lexical and semantic features from contrastive text pairs, screens candidates using , and selects features by residual gain.
result LFD features achieve higher human-human and human-LLM agreement than baseline concepts and are less label-leaking.
ShapleyBO explains BO's decisions, enhancing human-AI collaboration in robotics.
problem Lack of explainability in BO's black box nature, especially in human-in-the-loop applications.
method Uses game-theoretic Shapley values to quantify and interpret BO's parameter contributions.
result ShapleyBO identifies exploration and exploitation contributions, disentangling aleatoric and epistemic uncertainty.
Lean Copilot uses LLMs to assist theorem proving in Lean, improving efficiency and automation.
problem Challenges in using existing neural theorem provers to prove novel theorems autonomously.
method Introduces Lean Copilot, a framework for integrating LLMs into Lean's theorem proving process.
result Lean Copilot automates 74.2% of proof steps on average, significantly improving over existing methods.
The automatic detection of frauds in banking transactions has been recently studied as a way to help the analysts finding fraudulent operations. Due to the availability of a human feedback, this task has been studied in the framework of active learning: the fraud predictor is allowed to sequentially call on an oracle. …
Optimizes classifiers for varying levels of automation.
problem Supervised learning models often perform worse than human experts on specific instances.
method Focuses on convex margin-based classifiers, showing the problem is NP-hard. For SVMs, the objective function is decomposed into monotone and modular components, allowing efficient algorithms to solve the problem.
result The approach demonstrates that classifiers optimized for varying levels of automation can outperform full automation and human-only models.
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…
Generative model improves safety in self-driving simulators and human motion generation.
problem Improving generative models for constrained domains like safety-critical applications.
method Developed Gen-neG, a denoising diffusion model that uses oracle-assisted guidance.
result Empirically validated Gen-neG for collision avoidance and safety-guarded human motion generation.
Intelli-Paint improves painting efficiency and naturalness.
problem Artwork generation is time-consuming and requires high proficiency.
method Intelli-Paint uses a progressive layering and sequential brushstroke guidance strategy.
result The approach reduces brushstrokes by ~60-80% without compromising quality.
Generative AI at Workecon.GN
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.
Recent variants improve knowledge distillation performance.
problem Improving the performance of knowledge distillation.
method Introducing additional components or changing the learning process.
result These variants have shown promising results.
Human activity recognition using smart home sensors is one of the bases of ubiquitous computing in smart environments and a topic undergoing intense research in the field of ambient assisted living. The increasingly large amount of data sets calls for machine learning methods. In this paper, we introduce a deep learnin…
A framework helps reinforcement learning agents understand and decompose tasks from human demonstrations.
problem Sparse-reward tasks where demonstrations are used as sources of causal knowledge.
method Develops causal models through observation and reasons from this knowledge to decompose tasks.
result A basic implementation of Reasoning from Demonstration (RfD) is effective in sparse-reward tasks.
Despite the advantages of all-weather and all-day high-resolution imaging, SAR remote sensing images are much less viewed and used by general people because human vision is not adapted to microwave scattering phenomenon. However, expert interpreters can be trained by compare side-by-side SAR and optical images to learn…
CausalForge automates causal inference research with formal proofs and self-improvement.
problem Unreliable evaluation of automated research results by large language models.
method Formal proof assistant (Lean) and self-improving agentic pipeline.
result Automated research produces reliable formal proofs and artifacts.
Inferring intent from observed behavior has been studied extensively within the frameworks of Bayesian inverse planning and inverse reinforcement learning. These methods infer a goal or reward function that best explains the actions of the observed agent, typically a human demonstrator. Another agent can use this infer…
Online Decision Mediationstat.ML
An assistant learns to mediate decisions between humans and experts, balancing risk and learning.
problem Learning to mediate decisions between imperfect humans and expert knowledge.
method Formalizes online decision mediation, proposes a policy to balance immediate loss and future generalization.
result Consistent gains over benchmarks in decision-making performance.
Measuring the Prevalence of Policy Violating Content with ML Assisted Sampling and LLM Labelingcs.LG
Measures policy-violating content prevalence with ML-assisted sampling and LLM labeling.
problem Accurate measurement of content violations that are often rare and costly to label.
method Design-based measurement system using ML-assisted probability sampling and LLM labeling.
result Produces unbiased prevalence estimates with confidence intervals and dashboard drilldowns.
Collaborative Learning of Semi-Supervised Clustering and Classification for Labeling Uncurated Datacs.LG
Plud system reduces labeling time and produces accurate models for uncategorized images.
problem Time-consuming manual labeling of uncategorized images.
method Iterative semi-supervised workflow combining clustering and classification.
result Reduces labeling time and produces accurate models.
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.
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.
Robot-assisted dressing offers an opportunity to benefit the lives of many people with disabilities, such as some older adults. However, robots currently lack common sense about the physical implications of their actions on people. The physical implications of dressing are complicated by non-rigid garments, which can r…
DFKI Cabin Simulator tests visual monitoring functions in vehicles.
problem Validating novel human-vehicle interfaces and driver assistance systems.
method Driving simulator with in-cabin mock-up and camera system.
result Validation of in-cabin monitoring functions for advanced driver assistance and automated driving.
Conformal prediction helps quantify uncertainty but its use by humans is unclear.
problem Uncertainty quantification in predictions for human decision making.
method Decision theoretic framework for evaluating predictive uncertainty.
result Conformal prediction sets and human decision making goals are in tension.
In semantic parsing for question-answering, it is often too expensive to collect gold parses or even gold answers as supervision signals. We propose to convert model outputs into a set of human-understandable statements which allow non-expert users to act as proofreaders, providing error markings as learning signals to…
New feature representation improves HAR model accuracy.
problem Improving human activity recognition model performance.
method Proposed new feature representation and comparison with existing methods.
result Techniques based on the proposed representation outperform baselines.
Paper uses user engagement signals to automatically label training data for AI assistants.
problem Lack of annotated training data for AI assistants.
method Leverages user engagement signals for unsupervised entity labeling and data augmentation.
result Significant accuracy gains in sequence labeling tasks and user-facing results.
A novel controller for wheeled robots handles joystick inputs for smooth steering.
problem Steering control for differential-drive wheeled robots from indirect joystick inputs.
method Developed a geometric controller based on Darboux frame kinematics.
result Smooth trajectories achieved with safety constraints and no desired states.
In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction between human translation and the translation given by an NMT model. To achieve this goal, inspired by the recent success …
Robots learn intentions from multiple cues to reduce uncertainty.
problem Uncertainty in human-robot interaction for vulnerable users.
method Multimodal classifier fusion using Bayesian Independent Opinion Pool.
result Fused classifiers outperform individual modalities in accuracy and uncertainty reduction.
We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive that clear explanations from a knowledgeable teacher can significantly improve a …
Deep learning improves death cause coding accuracy.
problem Geospatial discrepancies in human-coded death certificates.
method Deep artificial neural network model trained on CépiDc database.
result 97.8% accuracy in automated coding compared to 75% for Iris software.
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.
Decisions by Machine Learning (ML) models have become ubiquitous. Trusting these decisions requires understanding how algorithms take them. Hence interpretability methods for ML are an active focus of research. A central problem in this context is that both the quality of interpretability methods as well as trust in ML…
The problem of human activity recognition is central for understanding and predicting the human behavior, in particular in a prospective of assistive services to humans, such as health monitoring, well being, security, etc. There is therefore a growing need to build accurate models which can take into account the varia…
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.