让大模型内部对话动作可控，提升回复准确率12.5点
Latent-IM: Latent Interaction Management for Speech LLMs
- 在大模型内部构建对话动作管理机制，分离选择与生成
- 相比原始模型，对话动作准确率提升12.5个百分点
- 无需微调即可实现人类水平动作选择，适合对话系统研究者
传统语音对话系统将对话管理与响应生成分离：策略决定下一步动作，生成组件执行该动作。随着对话系统向大语言模型（LLM）演进，这种分离已消失于模型隐层表示中。本文探讨是否可在LLM内部恢复类似状态估计与动作控制的机制，以管理确认、询问、解释、回复等对话动作。将动作控制建模为两个耦合问题：选择（根据上下文预测合适动作）与实现（生成时因果地输出选定动作）。提出Latent-IM框架，提供通用接口，在不同目标下选择并部署对话动作。实验表明，该方法可复现人类动作选择，在端到端动作准确率上比未引导的基线模型提升12.5个百分点，且性能接近微调方案。
原文摘要 · Abstract (English)
Classical spoken dialogue systems often separated dialogue management from response realization: a policy selected the next dialogue action, and a generation component expressed that action. As dialogue systems shift toward LLMs, this decomposition has largely disappeared into the model's hidden representations. We ask whether an LLM-internal analogue of state estimation and action control can be recovered for conversational moves such as acknowledging, checking, querying, explaining, and replying. We formulate move control as two coupled problems: selection, predicting the appropriate next move from the dialogue context, and realization, causally producing a chosen move at generation time. We introduce Latent-IM, an internal dialogue-management framework that provides a general interface for choosing and deploying conversational moves under different objectives. Here, we use this control to reproduce human move choices, improving average end-to-end move accuracy by 12.5 points over the unsteered backbone while performing comparably to fine-tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。