Low-Burden LLM-Based Preference Learning: Personalizing Assistive Robots from Natural Language Feedback for Users with Paralysis

arXiv:2604.01463 · cs.RO, cs.AI, cs.HC · Submitted 2026-04-01 · Read on arXiv

cs.RO, cs.AI, cs.HC

Submitted: 2026-04-01

Updated: 2026-06-12

Comments: Accepted to IEEE RO-MAN 2026

Journal ref: 2026 IEEE 35th International Conference on Robot and Human Interactive Communication (RO-MAN)

DOI: 10.1109/RO-MAN72286.2026.11714899

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Decode — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 8 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes

Sources

• Eliciting Human Preferences with Language Models
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• Preference Leakage: A Contamination Problem in LLM-as-a-judge

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies