相关论文: Improved Instruction Ordering in Recipe-Grounded C…

Instruction tuning has been shown to be able to improve cross-task generalization of language models. However, it is still challenging for language models to complete the target tasks following the instructions, as the instructions are…

This paper describes a dialogue system developed for the Dialogue Robot Competition 2023 that achieves topic control for trip planning by inserting text into prompts using the ChatGPT-API. We built a system that is capable of generating…

Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the same natural language task can be explained with the same task…

Goal oriented dialogue systems have become a prominent customer-care interaction channel for most businesses. However, not all interactions are smooth, and customer intent misunderstanding is a major cause of dialogue failure. We show that…

Pre-trained large language models, such as ChatGPT, archive outstanding performance in various reasoning tasks without supervised training and were found to have outperformed crowdsourcing workers. Nonetheless, ChatGPT's performance in the…

Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…

This work presents a new dialog dataset, CookDial, that facilitates research on task-oriented dialog systems with procedural knowledge understanding. The corpus contains 260 human-to-human task-oriented dialogs in which an agent, given a…

The rapid evolution of Large Language Models (LLMs) has enabled the industry to develop various AI-based services. Instruction tuning is considered essential in adapting foundation models for target domains to provide high-quality services…

Making language models bigger does not inherently make them better at following a user's intent. For example, large language models can generate outputs that are untruthful, toxic, or simply not helpful to the user. In other words, these…

Large pre-trained language models have exhibited unprecedented capabilities in producing high-quality text via prompting techniques. This fact introduces new possibilities for data collection and annotation, particularly in situations where…

Semantic parsing of user-generated instructional text, in the way of enabling end-users to program the Internet of Things (IoT), is an underexplored area. In this study, we provide a unique annotated corpus which aims to support the…

Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant…

ChatGPT has achieved remarkable success in natural language understanding. Considering that recommendation is indeed a conversation between users and the system with items as words, which has similar underlying pattern with ChatGPT, we…

As conversational search becomes more pervasive, it becomes increasingly important to understand the user's underlying information needs when they converse with such systems in diverse domains. We conduct an in-situ study to understand…

Traditional dialog systems used in goal-oriented applications require a lot of domain-specific handcrafting, which hinders scaling up to new domains. End-to-end dialog systems, in which all components are trained from the dialogs…

The number of robots deployed in our daily surroundings is ever-increasing. Even in the industrial set-up, the use of coworker robots is increasing rapidly. These cohabitant robots perform various tasks as instructed by co-located human…

Following complex instructions in conversational assistants can be quite daunting due to the shorter attention and memory spans when compared to reading the same instructions. Hence, when conversational assistants walk users through the…

Chain-of-Thought (CoT) prompting can effectively elicit complex multi-step reasoning from Large Language Models~(LLMs). For example, by simply adding CoT instruction ``Let's think step-by-step'' to each input query of MultiArith dataset,…

Mixed-initiative dialogue tasks involve repeated exchanges of information and conversational control. Conversational agents gain control by generating responses that follow particular dialogue intents or strategies, prescribed by a policy…

Current instruction data synthesis methods primarily focus on single-turn instructions and often neglect cross-turn coherence, resulting in context drift and reduced task completion rates in extended conversations. To address this…