我们在论文中提出了一个具有高通用性和可迁移性的四步骤数据集构建流程，并基于此构造了一个多领域任务导向型的中文对话数据集TransferTOD，可以涵盖更为复杂和多样的对话任务，模拟更为真实的对话情景。 消融实验证明了我们的数据不仅具备出色的抗干扰能力，在提问环节所体现的语言能力上还具备良好的多样性和流畅性。 实验证据表明，我们所提供的数据集有着十分卓越的性能。 我们基于它进行SFT之后得到的TransferTOD-7B 模型不仅可以根据所缺槽位主动向用户 …

提出了ProToD(主动目标驱动的llm诱导ToD)方法，该方法预测未来的对话行动，并集成了目标导向的奖励信号，提高了ToD系统的效率和成功。 为了更好、灵活地评估llm诱导ToD系统的效率和成功率，引入了基于GPT-4的目标驱动用户仿真来评估ToD系统的性能。

阐述多轮对话系统的最新进展，包括基于llm的 开放域对话 （odd）和 任务型对话 （tod）系统 讨论一些未来的重点和因LLMS发展及对多轮对话系统日益而增的需求带来的研究问题

6 天之前 · In this work, we introduce SGP-TOD, Schema-Guided Prompting for building Task-Oriented Dialog systems effortlessly based on large language models (LLMs). Utilizing the predefined task schema, i.e., belief instruction and dialog policy, we instruct fixed LLMs to generate appropriate responses on novel tasks, without the need for training data.

2023年9月16日 · To fill these gaps, we introduce the ProToD (Proactively Goal-Driven LLM-Induced ToD) approach, which anticipates the future dialogue actions and incorporates the goal-oriented reward signal to enhance ToD systems. Additionally, we present a novel evaluation method that assesses ToD systems based on goal-driven dialogue simulations.

2023年5月15日 · In this work, we introduce SGP-TOD, Schema-Guided Prompting for building Task-Oriented Dialog systems effortlessly based on LLMs. Utilizing the symbolic knowledge -- task schema, we instruct fixed LLMs to generate appropriate responses on novel tasks, circumventing the need for training data.

HR-Multiwoz is a fully-labeled dataset of 550 conversations spanning 10 HR domains to evaluate LLM Agent. It is the first labeled open-sourced conversation dataset in the HR domain for NLP research. In this repo we provides a detailed recipe for the data generation procedure described in the paper along with data analysis and human evaluations.

2024年7月9日 · 面向任务的对话（tod）系统是一种人工智能技术，旨在通过自然语言理解用户的指令或请求，并通过与用户进行对话来完成特定的任务。这类系统广泛应用于客服机器人、个人助理软件等场景，能够处理如预订酒店、查询天气...

2024年10月14日 · 4. LLM在task-oriented dialogue system（TOD）中的应用. TOD 系统通过交互式对话协助用户达成特定领域相关的目标，诸如酒店预订或餐厅查询。鉴于其显著的效用，近年来该技术已引起研究人员日益增多的关注。

2023年10月31日 · To fill these gaps, we introduce the ProToD (Proactively Goal-Driven LLM-Induced ToD) approach, which anticipates the future dialogue actions and incorporates the goal-oriented reward signal to enhance ToD systems. Additionally, we present a novel evaluation method that assesses ToD systems based on goal-driven dialogue simulations.