Conference Open access

Generalizing Bayesian Human-AI Collaboration: Theory and Application in Data-Scarce Environments

Peng Liu Hai-Long Sun C. Teo Mabel C. Chou

Sep 2026 · Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence · 0 citations · 17 references

TL;DR

This work proposes a flexible Bayesian framework that significantly outperforms standalone ResNet, human, and LLM-based approaches, demonstrating the practical benefits of fusing these heterogeneous signal sources.

Abstract

Combining predictions from heterogeneous classifiers—such as in-house deep learning models, human experts, and large language models (LLMs)—is a key challenge, especially in data-scarce environments such as humanitarian operations. We propose a flexible Bayesian framework to effectively fuse these diverse inputs. By integrating classifier logits with auxiliary human feedback (e.g., confidence, image clarity) using an ordered probit process, our model generalizes prior work to accommodate the real-world properties of these classifiers. We validate our framework on a challenging product recognition task in food bank operations, an environment defined by data scarcity and an inexperienced volunteer workforce. Our combined model significantly outperforms standalone ResNet, human, and LLM-based approaches, demonstrating the practical benefits of fusing these heterogeneous signal sources.

DOI Semantic Scholar

Read PDF

Similar papers

Open access 2023

Self-Supervised Learning Techniques for Large-Scale AI Systems

Experimental results demonstrate that SSL outperforms traditional supervised learning in accuracy, scalability, and transferability, while also reducing data labeling costs.

Shalini Gupta · International Journal of Inn... · 0 citations

Preprint Jul 2026

Robust Human-AI Complementarity under Uncertainty

It is shown that a key factor is the error correlation structure between human and AI predictions, and when the AI's prediction errors are negatively correlated with those of the human, the decision maker can construct robust strategies which guarantee improvements in expected utility.

Yewon Byun, Bryan Wilder · 0 citations

Open access Aug 2026

Mental bootstrapping enables human-level concept learning in self-supervised deep models

A self-supervised framework that trains models on systematically simplified versions of abstract reasoning tasks containing incomplete but structured concept cues enables models to form internal abstractions under limited resources and later apply them to more complex problems.

Lingxiao Yang, Muyang Lyu, Ying-Jie Wang et al. · Science Advances · 0 citations

Conference Open access Sep 2026

Toward Data-Efficient Intelligence: From Few-Shot Learning to Agentic Systems

A research path from few-shot learning to meta-learning, in-context learning, and data-efficient agentic systems is summarized, which concludes that limited supervision can be made useful by the right priors, the right adaptation mechanism, and the right way to reuse experience.

Ya-Qing Wang · Proceedings of the Thirty-Fi... · 0 citations

Preprint Aug 2026

A Heterogeneous Mixture of Experts Framework for Interpretable Machine Learning

The proposed approach combines interpretability, adaptive inductive bias selection, and probabilistic coherence within a unified mixture-of-experts framework to achieve interpretable expert assignments while achieving predictive performance competitive with homogeneous MoDT and Random Forests.

Soham Chatterjee, Rwitobroto Dey, Smarajit Bose · 0 citations

#artificial intelligence Preprint Aug 2026

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

This work introduces Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers, and shows that unsupervised reasoning can emerge through cooperative multi-agent training.

Yunhao Yang, Yuexin Bian, Yun-Jie Tian et al. · 1 citation