Rethinking Opinion Measurement Interfaces for Human-in-the-Loop Optimization

arXiv:2610.14757 · cs.HC, cs.LG · Submitted 2026-10-10 · Read on arXiv

cs.HC, cs.LG

Submitted: 2026-10-10

Updated: 2026-10-10

Code: https://github.com/pytorch/botorch

Project page: https://react-dnd.github.io/react-dnd/about

Terminology

• Human-in-the-Loop — 1× in this paper · explained in 3 episodes

Sources

• Fitting Linear Mixed-Effects Models using lme4
• Choice functions based multi-objective Bayesian optimisation
• How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models
• The Curious Case of Neural Text Degeneration
• BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
• High-Resolution Image Synthesis with Latent Diffusion Models
• The reparameterization trick for acquisition functions

Related papers

• Calibrating LLM Explanations to Human Decisions with Reinforcement Learning
• EduGage: A Multimodal Dataset and Benchmark for Sensor-Based Momentary Assessment of Engagement in Self-Guided Video Learning
• EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution
• HAGI++: Head-Assisted Gaze Imputation and Generation
• Explanation User Interfaces: A Systematic Literature Review
• Hybrid Cinematography: Previsualizing and Managing Hallucination Risk in Generative Video Reshooting