# Few-Shot Inference of Human Perceptions of Robot Performance in Social Navigation Scenarios

arXiv: https://arxiv.org/abs/2512.16019 · HTML: https://mlsanity.com/paper/2512.16019/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 63 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks](https://mlsanity.com/paper/2302.08399/) (2023)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [Evaluating Large Language Models in Theory of Mind Tasks](https://mlsanity.com/paper/2302.02083/) (2023)
- [Large Language Models as General Pattern Machines](https://mlsanity.com/paper/2307.04721/) (2023)
- [Active Example Selection for In-Context Learning](https://mlsanity.com/paper/2211.04486/) (2022)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [Core Challenges of Social Robot Navigation: A Survey](https://mlsanity.com/paper/2103.05668/) (2021)
- [Can LLM be a Personalized Judge?](https://mlsanity.com/paper/2406.11657/) (2024)
- [Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics](https://mlsanity.com/paper/2403.19578/) (2024)
- [LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models](https://mlsanity.com/paper/2309.14393/) (2023)
- [In-Context Learning Enables Robot Action Prediction in LLMs](https://mlsanity.com/paper/2410.12782/) (2024)
- [Theory of Mind abilities of Large Language Models in Human-Robot Interaction : An Illusion?](https://mlsanity.com/paper/2401.05302/) (2024)
- [A Protocol for Validating Social Navigation Policies](https://mlsanity.com/paper/2204.05443/) (2022)
- [Personalized Adaptation via In-Context Preference Learning](https://mlsanity.com/paper/2410.14001/) (2024)

## Abstract (arXiv)

Understanding how humans evaluate robot behavior during human-robot interactions is crucial for developing socially aware robots that behave according to human expectations. While the traditional approach to capturing these evaluations is to conduct a user study, recent work has proposed utilizing machine learning instead. However, existing data-driven methods require large amounts of labeled data, which limits their use in practice. To address this gap, we propose leveraging the few-shot learning capabilities of Large Language Models (LLMs) to improve how well a robot can predict a user's perception of its performance, and study this idea experimentally in social navigation tasks. To this end, we extend the SEAN TOGETHER dataset with additional real-world human-robot navigation episodes and participant feedback. Using this augmented dataset, we evaluate the ability of several LLMs to predict human perceptions of robot performance from a small number of in-context examples, based on observed spatio-temporal cues of the robot and surrounding human motion. Our results demonstrate that LLMs can match or exceed the performance of traditional supervised learning models while requiring an order of magnitude fewer labeled instances. We further show that prediction performance can improve with more in-context examples, confirming the scalability of our approach. Additionally, we investigate what kind of sensor-based information an LLM relies on to make these inferences by conducting an ablation study on the input features considered for performance prediction. Finally, we explore the novel application of personalized examples for in-context learning, i.e., drawn from the same user being evaluated, finding that they further enhance prediction accuracy. This work paves the path to improving robot behavior in a scalable manner through user-centered feedback.