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

• URL: http://arxiv.org/abs/2602.23312v1
• Date: Thu, 26 Feb 2026 18:20:26 GMT
• Title: Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction
• Authors: Rafael R. Baptista, André de Lima Salgado, Ricardo V. Godoy, Marcelo Becker, Thiago Boaventura, Gustavo J. G. Lahr,
• Abstract summary: Leader-follower interaction is an important paradigm in human-robot interaction (HRI)<n>Small language models (SLMs) offer a potential alternative, but their effectiveness for role classification in HRI has not been systematically evaluated.
• Score: 1.3511057160494195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Grounded Test-Time Adaptation for LLM Agents [75.62784644919803]
  Large language model (LLM)-based agents struggle to generalize to novel and complex environments.<n>We propose two strategies for adapting LLM agents by leveraging environment-specific information available during deployment.
  arXiv  Detail & Related papers  (2025-11-06T22:24:35Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Neural Models and Language Model Prompting for the Multidimensional Evaluation of Open-Ended Conversations [1.0006801729628605]
  We develop models to predict dialogue-level, dimension-specific scores.<n>Our work follows two main strategies: employing Language Models (LMs) as evaluators through prompting, and training encoder-based classification and regression models.<n>Although their performance decreases on the test set, it is important to note that the test set contains annotations with significantly different score ranges for some of the dimensions with respect to the train and validation sets.
  arXiv  Detail & Related papers  (2025-08-31T13:24:05Z)
• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• RoHOI: Robustness Benchmark for Human-Object Interaction Detection [84.78366452133514]
  Human-Object Interaction (HOI) detection is crucial for robot-human assistance, enabling context-aware support.<n>We introduce the first benchmark for HOI detection, evaluating model resilience under diverse challenges.<n>Our benchmark, RoHOI, includes 20 corruption types based on the HICO-DET and V-COCO datasets and a new robustness-focused metric.
  arXiv  Detail & Related papers  (2025-07-12T01:58:04Z)
• Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback [59.768119380109084]
  This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback.<n>We propose RiCL, a Reinforced interactive Continual Learning framework leveraging Large Language Models (LLMs)<n>Our RiCL approach substantially outperforms existing combinations of state-of-the-art online continual learning and noisy-label learning methods.
  arXiv  Detail & Related papers  (2025-05-15T03:22:03Z)
• Detect, Explain, Escalate: Low-Carbon Dialogue Breakdown Management for LLM-Powered Agents [30.13634341221476]
  Large Language Models (LLMs) are transforming numerous applications, but their susceptibility to conversational breakdowns remains a critical challenge undermining user trust.<n>This paper introduces a "Detect, Explain, Escalate" framework to manage dialogue breakdowns in LLM-powered agents, emphasizing low-carbon operation.
  arXiv  Detail & Related papers  (2025-04-26T07:51:05Z)
• Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN [20.380620709345898]
  Early-exiting dynamic neural networks (EDNN) allow a model to make some of its predictions from intermediate layers (i.e., early-exit) Training an EDNN architecture is challenging as it consists of two intertwined components: the gating mechanism (GM) that controls early-exiting decisions and the intermediate inference modules (IMs) that perform inference from intermediate representations. We propose a novel architecture that connects these two modules. This leads to significant performance improvements on classification datasets and enables better uncertainty characterization capabilities.
  arXiv  Detail & Related papers  (2023-10-13T14:56:38Z)
• Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
  We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU) We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
  arXiv  Detail & Related papers  (2020-01-28T22:09:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.