# Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction

arXiv: https://arxiv.org/abs/2602.23312 · HTML: https://mlsanity.com/paper/2602.23312/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [LLM-based NLG Evaluation: Current Status and Challenges](https://mlsanity.com/paper/2402.01383/) (2024)
- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities](https://mlsanity.com/paper/2408.13296/) (2024)
- [Synthetic Data Generation Using Large Language Models: Advances in Text and Code](https://mlsanity.com/paper/2503.14023/) (2025)
- [RAFT: A Real-World Few-Shot Text Classification Benchmark](https://mlsanity.com/paper/2109.14076/) (2021)
- [Fine-tuning BERT for Low-Resource Natural Language Understanding via Active Learning](https://mlsanity.com/paper/2012.02462/) (2020)
- [LaMI: Large Language Models for Multi-Modal Human-Robot Interaction](https://mlsanity.com/paper/2401.15174/) (2024)
- [Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation](https://mlsanity.com/paper/2308.16797/) (2023)
- [An Empirical Evaluation of Prompting Strategies for Large Language Models in Zero-Shot Clinical Natural Language Processing](https://mlsanity.com/paper/2309.08008/) (2023)
- [Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art](https://mlsanity.com/paper/2403.16527/) (2024)
- [Few-shot LLM Synthetic Data with Distribution Matching](https://mlsanity.com/paper/2502.08661/) (2025)
- [Multilingual Prompts in LLM-Based Recommenders: Performance Across Languages](https://mlsanity.com/paper/2409.07604/) (2024)
- [Are We There Yet? A Measurement Study of Efficiency for LLM Applications on Mobile Devices](https://mlsanity.com/paper/2504.00002/) (2025)
- [Enhancing Human-Robot Collaborative Assembly in Manufacturing Systems Using Large Language Models](https://mlsanity.com/paper/2406.01915/) (2024)
- [Human Leading or Following Preferences: Effects on Human Perception of the Robot and the Human-Robot Collaboration](https://mlsanity.com/paper/2401.01466/) (2024)

## Abstract (arXiv)

Leader-follower interaction is an important paradigm in human-robot interaction (HRI). Yet, assigning roles in real time remains challenging for resource-constrained mobile and assistive robots. While large language models (LLMs) have shown promise for natural communication, their size and latency limit on-device deployment. Small language models (SLMs) offer a potential alternative, but their effectiveness for role classification in HRI has not been systematically evaluated. In this paper, we present a benchmark of SLMs for leader-follower communication, introducing a novel dataset derived from a published database and augmented with synthetic samples to capture interaction-specific dynamics. We investigate two adaptation strategies: prompt engineering and fine-tuning, studied under zero-shot and one-shot interaction modes, compared with an untrained baseline. Experiments with Qwen2.5-0.5B reveal that zero-shot fine-tuning achieves robust classification performance (86.66% accuracy) while maintaining low latency (22.2 ms per sample), significantly outperforming baseline and prompt-engineered approaches. However, results also indicate a performance degradation in one-shot modes, where increased context length challenges the model's architectural capacity. These findings demonstrate that fine-tuned SLMs provide an effective solution for direct role assignment, while highlighting critical trade-offs between dialogue complexity and classification reliability on the edge.