Related papers: ConsistentChat: Building Skeleton-Guided Consisten…

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…

In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants. In these dialogues, it is important to identify user's goals automatically to resolve their…

Conversational AI has now reached billions of users, yet existing datasets capture only what people say, not what they think. We introduce ThoughtTrace, the first large-scale dataset that pairs real-world multi-turn human--AI conversations…

In-context learning with Large Language Models (LLMs) has emerged as a promising avenue of research in Dialog State Tracking (DST). However, the best-performing in-context learning methods involve retrieving and adding similar examples to…

Conversational systems are of primary interest in the AI community. Chatbots are increasingly being deployed to provide round-the-clock support and to increase customer engagement. Many of the commercial bot building frameworks follow a…

Neural Chat Translation (NCT) aims to translate conversational text between speakers of different languages. Despite the promising performance of sentence-level and context-aware neural machine translation models, there still remain…

Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach for multi-modal dialogue. However, due to the limited…

Real-time speech interaction, serving as a fundamental interface for human-machine collaboration, holds immense potential. However, current open-source models face limitations such as high costs in voice data collection, weakness in dynamic…

The development of AI for mental health is hindered by a lack of authentic therapy dialogues, due to strict privacy regulations and the fact that clinical sessions were historically rarely recorded. We present an LLM-driven pipeline that…

Dialogue state tracking (DST) aims to extract essential information from multi-turn dialogue situations and take appropriate actions. A belief state, one of the core pieces of information, refers to the subject and its specific content, and…

Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote in a conversation is challenging for both humans and machines. This work studies automatic quotation…

Large language models (LLMs) are increasingly relied upon for complex multi-turn conversations across diverse real-world applications. However, existing benchmarks predominantly focus on single-turn evaluations, overlooking the models'…

Reasoning over sequences of images remains a challenge for multimodal large language models (MLLMs). While recent models incorporate multi-image data during pre-training, they still struggle to recognize sequential structures, often…

Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Although neural conversation models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We present a new end-to-end approach to…

Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods are…

Unlike traditional cascaded pipelines, end-to-end (E2E) spoken dialogue systems preserve full differentiability and capture non-phonemic information, making them well-suited for modeling spoken interactions. However, existing E2E approaches…

This study addresses the structural complexity and semantic ambiguity in stakeholder interactions within the Education-Industry Integration (EII) system. The scarcity of real interview data, absence of structured variable modeling, and lack…

Conversational Speech Synthesis (CSS) aims to align synthesized speech with the emotional and stylistic context of user-agent interactions to achieve empathy. Current generative CSS models face interpretability limitations due to…