Related papers: MORPHEUS: Modeling Role from Personalized Dialogue…

Natural language generators (NLGs) for task-oriented dialogue typically take a meaning representation (MR) as input. They are trained end-to-end with a corpus of MR/utterance pairs, where the MRs cover a specific set of dialogue acts and…

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…

Integrating argumentation mechanisms into negotiation dialogue systems improves conflict resolution through exchanges of arguments and critiques. Moreover, incorporating personality attributes enhances adaptability by aligning interactions…

This study presents RoleCraft-GLM, an innovative framework aimed at enhancing personalized role-playing with Large Language Models (LLMs). RoleCraft-GLM addresses the key issue of lacking personalized interactions in conversational AI, and…

Traditional UX development methodologies focus on developing ``one size fits all" solutions and lack the flexibility to cater to diverse user needs. In response, a growing interest has arisen in developing more dynamic UX frameworks.…

Existing open-domain dialogue generation models are usually trained to mimic the gold response in the training set using cross-entropy loss on the vocabulary. However, a good response does not need to resemble the gold response, since there…

The personalized dialogue explores the consistent relationship between dialogue generation and personality. Existing personalized dialogue agents model persona profiles from three resources: sparse or dense persona descriptions and dialogue…

With the rapid development of large language models, AI assistants like ChatGPT have become increasingly integrated into people's works and lives but are limited in personalized services. In this paper, we present a plug-and-play framework…

Building role-playing agents (RPAs) that faithfully emulate specific characters remains challenging because collecting character-specific utterances and continually updating model parameters are resource-intensive, making…

Autoregressive models used to generate responses in open-domain dialogue systems often struggle to take long-term context into account and to maintain consistency over a dialogue. Previous research in open-domain dialogue generation has…

Previous research on multi-party dialogue generation has predominantly leveraged structural information inherent in dialogues to directly inform the generation process. However, the prevalence of colloquial expressions and incomplete…

In this study, we explore the application of Large Language Models (LLMs) for generating synthetic users and simulating user conversations with a task-oriented dialogue system and present detailed results and their analysis. We propose a…

We study video-grounded dialogue generation, where a response is generated based on the dialogue context and the associated video. The primary challenges of this task lie in (1) the difficulty of integrating video data into pre-trained…

Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training gap where…

Multimodal Dialogue Response Generation (MDRG) is a recently proposed task where the model needs to generate responses in texts, images, or a blend of both based on the dialogue context. Due to the lack of a large-scale dataset specifically…

In order to build self-consistent personalized dialogue agents, previous research has mostly focused on textual persona that delivers personal facts or personalities. However, to fully describe the multi-faceted nature of persona, image…

Using a sequence-to-sequence framework, many neural conversation models for chit-chat succeed in naturalness of the response. Nevertheless, the neural conversation models tend to give generic responses which are not specific to given…

Developing language model-based dialogue agents requires effective data to train models that can follow specific task logic. However, most existing data simulation methods focus on increasing diversity in language, topics, or dialogue acts…

Much of NLP research has focused on crowdsourced static datasets and the supervised learning paradigm of training once and then evaluating test performance. As argued in de Vries et al. (2020), crowdsourced data has the issues of lack of…

The development of chatbots requires collecting a large number of human-chatbot dialogues to reflect the breadth of users' sociodemographic backgrounds and conversational goals. However, the resource requirements to conduct the respective…