Low-Burden LLM-Based Preference Learning: Personalizing Assistive Robots from Natural Language Feedback for Users with Paralysis
On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
Abstract (arXiv)
Physically Assistive Robots require personalized behaviors to ensure user safety and comfort. However, traditional preference learning methods, like exhaustive pairwise comparisons, cause substantial physical and cognitive fatigue for users with severe motor impairments. To solve this, we propose a low-burden, offline framework that translates unstructured natural language feedback directly into deterministic robotic control policies. To safely bridge the gap between ambiguous human speech and robotic code, our pipeline uses Large Language Models (LLMs) grounded in the Occupational Therapy Practice Framework. This clinical reasoning decodes subjective user reactions into explicit physical and psychological needs, which are then mapped into transparent decision trees. Before deployment, an automated "LLM-as-a-Judge" verifies the code's structural safety. We validated this system in a simulated meal preparation study with 10 adults with paralysis. Results show our natural language approach significantly reduces user workload compared to traditional baselines. Additionally, occupational therapists confirmed the generated policies are safe and accurately reflect user preferences.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 11 of its 40 references that are in the map. First posted on arXiv 1 Apr 2026.
Builds on
11 of 40 references.
References · 11
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
- 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
- 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
- 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
- 2021SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarizationcited by 402
- 2021AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Promptscited by 265
- 2025Preference Leakage: A Contamination Problem in LLM-as-a-judgecited by 119
- 2023Eliciting Human Preferences with Language Modelscited by 90
- 2021The Design of Stretch: A Compact, Lightweight Mobile Manipulator for Indoor Human Environmentscited by 39
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026StretchBot: A Neuro-Symbolic Framework for Adaptive Guidance with Assistive Robots ↗
- 2026HARMONI: Multimodal Personalization of Multi-User Human-Robot Interactions with LLMs
- 2025Efficiently Generating Expressive Quadruped Behaviors via Language-Guided Preference Learning
- 2024Enhancing Robotic Manipulation with AI Feedback from Multimodal Large Language Models
- 2024SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine
- 2025LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning
- 2024To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions
- 2024Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots