Related papers: GODEL: Large-Scale Pre-Training for Goal-Directed …

Pre-trained language models (PLM) have marked a huge leap in neural dialogue modeling. While PLMs are pre-trained on large-scale text corpora, they are usually fine-tuned on scarce dialogue data with specific domain knowledge and dialogue…

Task-oriented dialogue (TOD) systems enable users to achieve their goals through natural language interactions. Traditionally, these systems have relied on turn-level manually annotated metadata, such as dialogue states and policy…

Task-oriented dialogue (TOD) system is designed to accomplish user-defined tasks through dialogues. The TOD system has progressed towards end-to-end modeling by leveraging pre-trained large language models. Fine-tuning the pre-trained…

The recent success of large pre-trained language models such as BERT and GPT-2 has suggested the effectiveness of incorporating language priors in downstream dialog generation tasks. However, the performance of pre-trained models on the…

Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…

In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the…

Training Large Language Models (LLMs) to follow user instructions has been shown to supply the LLM with ample capacity to converse fluently while being aligned with humans. Yet, it is not completely clear how an LLM can lead a plan-grounded…

In this paper, we investigate the use of large language models (LLMs) like ChatGPT for document-grounded response generation in the context of information-seeking dialogues. For evaluation, we use the MultiDoc2Dial corpus of task-oriented…

Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded…

The reproducibility and transparency of large language models are crucial for advancing open research, ensuring the trustworthiness of results, and enabling investigations into data and model biases, as well as potential risks. To this end,…

One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process. In an effort to move toward automated evaluation of…

Pre-trained language models have been successfully used in response generation for open-domain dialogue. Four main frameworks have been proposed: (1) Transformer-ED using Transformer encoder and decoder separately for source and target…

Evaluating the quality of open-domain chatbots has become increasingly reliant on LLMs acting as automatic judges. However, existing meta-evaluation benchmarks are static, outdated, and lacking in multilingual coverage, limiting their…

It is important to define meaningful and interpretable automatic evaluation metrics for open-domain dialog research. Standard language generation metrics have been shown to be ineffective for dialog. This paper introduces the FED metric…

Dialogue systems are a popular natural language processing (NLP) task as it is promising in real-life applications. It is also a complicated task since many NLP tasks deserving study are involved. As a result, a multitude of novel works on…

Task-oriented dialogue (TOD) systems facilitate users in executing various activities via multi-turn dialogues, but Large Language Models (LLMs) often struggle to comprehend these intricate contexts. In this study, we propose a novel…

Practical dialog systems need to deal with various knowledge sources, noisy user expressions, and the shortage of annotated data. To better solve the above problems, we propose CGoDial, new challenging and comprehensive Chinese benchmark…

Transformer-based pre-trained language models boost the performance of open-domain dialogue systems. Prior works leverage Transformer-based pre-trained language models to generate texts with desired attributes in two general approaches: (1)…

We study knowledge-grounded dialogue generation with pre-trained language models. Instead of pursuing new state-of-the-art on benchmarks, we try to understand if the knowledge stored in parameters of the pre-trained models is already enough…

Pre-trained language models have shown remarkable success in improving various downstream NLP tasks due to their ability to capture dependencies in textual data and generate natural responses. In this paper, we leverage the power of…