EnSToM：利用熵缩放引导向量增强对话系统的主题维持能力
EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance
AI总结：
针对小型大语言模型在任务型对话中难以维持主题一致性的问题，提出熵缩放引导向量方法EnSToM，根据输入不确定性动态调整引导强度，以较小数据规模显著提升主题遵循性能。
摘要：
小型大语言模型（sLLMs）具有轻量级和高效率的优势，使其适用于资源受限的环境。然而，sLLMs在面向任务的对话系统中往往难以维持主题一致性，而这对于服务聊天机器人等场景至关重要。具体而言，确保模型拒绝偏离主题或恶意的输入并遵循其预期功能非常重要，以防止潜在的滥用并维护可靠性。为此，现有的激活工程方法被提出用于在推理过程中操纵内部激活。虽然这些方法在某些场景下有效，但我们的初步实验揭示了它们在确保主题遵循方面的局限性。因此，为解决这一问题，我们提出了一种名为熵缩放引导向量用于主题维持（EnSToM）的新方法。EnSToM根据输入不确定性动态调整引导强度，使模型能够有效处理偏离主题的干扰项，同时保持主题内的准确性。我们的实验表明，与微调方法相比，EnSToM在相对较小的数据规模下取得了显著的性能提升。通过在不牺牲效率的情况下改进主题遵循，我们的方法为增强基于sLLM的对话系统提供了稳健的解决方案。
英文摘要：
Small large language models (sLLMs) offer the advantage of being lightweight and efficient, which makes them suitable for resource-constrained environments. However, sLLMs often struggle to maintain topic consistency in task-oriented dialogue systems, which is critical for scenarios such as service chatbots. Specifically, it is important to ensure that the model denies off-topic or malicious inputs and adheres to its intended functionality so as to prevent potential misuse and uphold reliability. Towards this, existing activation engineering approaches have been proposed to manipulate internal activations during inference. While these methods are effective in certain scenarios, our preliminary experiments reveal their limitations in ensuring topic adherence. Therefore, to address this, we propose a novel approach termed Entropy-scaled Steering vectors for Topic Maintenance (EnSToM). EnSToM dynamically adjusts the steering intensity based on input uncertainty, which allows the model to handle off-topic distractors effectively while preserving on-topic accuracy. Our experiments demonstrate that EnSToM achieves significant performance gain with a relatively small data size compared to fine-tuning approaches. By improving topic adherence without compromising efficiency, our approach provides a robust solution for enhancing sLLM-based dialogue systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
