让企业AI助手自动识别并澄清模糊问题，提升交互准确性。
ECLAIR: Enhanced Clarification for Interactive Responses
- 统一端到端框架，自动生成澄清问题并根据回复消歧。
- 支持多下游代理信息融合，增强上下文理解能力。
- 适合企业级对话系统开发，尤其需精准响应的场景。
我们提出ECLAIR（Enhanced CLArification for Interactive Responses），一种用于企业AI助手交互消歧的统一、端到端框架。ECLAIR能够针对用户查询中的模糊内容生成澄清问题，并基于用户回复进行歧义消除。我们设计了一种通用架构，可整合多个下游智能体的歧义信息，增强上下文感知能力，并支持企业自定义智能体定义。系统内还引入提供领域特定语境信息的专用智能体。通过实验对比少样本提示技术，验证了ECLAIR在澄清问题生成与歧义解决上的优越性能。
原文摘要 · Abstract (English)
We present ECLAIR (Enhanced CLArification for Interactive Responses), a novel unified and end-to-end framework for interactive disambiguation in enterprise AI assistants. ECLAIR generates clarification questions for ambiguous user queries and resolves ambiguity based on the user's response.We introduce a generalized architecture capable of integrating ambiguity information from multiple downstream agents, enhancing context-awareness in resolving ambiguities and allowing enterprise specific definition of agents. We further define agents within our system that provide domain-specific grounding information. We conduct experiments comparing ECLAIR to few-shot prompting techniques and demonstrate ECLAIR's superior performance in clarification question generation and ambiguity resolution.
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。