Related papers: TicketTalk: Toward human-level performance with en…
Current medical AI systems often fail to replicate real-world clinical reasoning, as they are predominantly trained and evaluated on static text and question-answer tasks. These tuning methods and benchmarks overlook critical aspects like…
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 this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback…
Talk2AI is a large-scale longitudinal dataset of 3,080 conversations (totaling 30,800 turns) between human participants and Large Language Models (LLMs), designed to support research on persuasion, opinion change, and human-AI interaction.…
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response…
In recommendation dialogs, humans commonly disclose their preference and make recommendations in a friendly manner. However, this is a challenge when developing a sociable recommendation dialog system, due to the lack of dialog dataset…
Improving user experience of a dialogue system often requires intensive developer effort to read conversation logs, run statistical analyses, and intuit the relative importance of system shortcomings. This paper presents a novel approach to…
Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…
Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network. This strategy tends to generate safe responses due to the mutual restriction between emotion and…
Recent advancements in conversational systems have significantly enhanced human-machine interactions across various domains. However, training these systems is challenging due to the scarcity of specialized dialogue data. Traditionally,…
Many users communicate with chatbots and AI assistants in order to help them with various tasks. A key component of the assistant is the ability to understand and answer a user's natural language questions for question-answering (QA).…
Pre-trained conversation models (PCMs) have demonstrated remarkable results in task-oriented dialogue (TOD) systems. Many PCMs focus predominantly on dialogue management tasks like dialogue state tracking, dialogue generation tasks like…
Effective feedback is essential for refining instructional practices in mathematics education, and researchers often turn to advanced natural language processing (NLP) models to analyze classroom dialogues from multiple perspectives.…
Task-oriented dialog(TOD) aims to assist users in achieving specific goals through multi-turn conversation. Recently, good results have been obtained based on large pre-trained models. However, the labeled-data scarcity hinders the…
Dialog evaluation is a challenging problem, especially for non task-oriented dialogs where conversational success is not well-defined. We propose to evaluate dialog quality using topic-based metrics that describe the ability of a…
To facilitate the research on intelligent and human-like chatbots with multi-modal context, we introduce a new video-based multi-modal dialogue dataset, called TikTalk. We collect 38K videos from a popular video-sharing platform, along with…
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…
Fact-based dialogue generation is a task of generating a human-like response based on both dialogue context and factual texts. Various methods were proposed to focus on generating informative words that contain facts effectively. However,…
Training task-oriented dialogue systems typically requires turn-level annotations for interacting with their APIs: e.g. a dialogue state and the system actions taken at each step. These annotations can be costly to produce, error-prone, and…
The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS systems, typically trained and inferenced on complete…