Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912962820702208 |
|---|---|
| author | Baptista, Rafael R. Salgado, André de Lima Godoy, Ricardo V. Becker, Marcelo Boaventura, Thiago Lahr, Gustavo J. G. |
| author_facet | Baptista, Rafael R. Salgado, André de Lima Godoy, Ricardo V. Becker, Marcelo Boaventura, Thiago Lahr, Gustavo J. G. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23312 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction Baptista, Rafael R. Salgado, André de Lima Godoy, Ricardo V. Becker, Marcelo Boaventura, Thiago Lahr, Gustavo J. G. Human-Computer Interaction Artificial Intelligence Machine Learning Robotics Systems and Control 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. |
| title | Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction |
| topic | Human-Computer Interaction Artificial Intelligence Machine Learning Robotics Systems and Control |
| url | https://arxiv.org/abs/2602.23312 |