One potential solution to help people change their eating behavior is to develop conversational systems able to recommend healthy recipes. Beyond the intrinsic quality of the recommendations themselve…
Proactive dialogue systems, related to a wide range of real-world conversational applications, equip the conversational agent with the capability of leading the conversation direction towards achievin…
  Existing dialogue corpora and models are typically designed under…
Amogh Mannekote, Bonnie J. Dorr, Kristy Elizabeth Boyer University of Florida “Automated negotiation support systems aim to help human negotiators reach more favorable outcomes in multi-issue negoti…
Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks. The recent success of large pre-trained language models has suggested the effectiv…
 Instruction-finetuned large language models (LLMs) gained a huge popularity recently, thanks to their ability to interact wi…
Existing dialogue models may encounter scenarios which are not well-represented in the training data, and as a result generate responses that are unnatural, inappropriate, or unhelpful. We propose the…
While information retrieval (IR) systems may provide answers for such user queries, they do not directly assist content creators—such as lecturers who want to improve their content—identify segments t…
Recent efforts have incorporated large language models (LLMs) with external resources (e.g., the Internet) or internal control flows (e.g., prompt chaining) for tasks requiring grounding or reasoning.…
In the field of natural language processing, open-domain chatbots have emerged as an important research topic. However, a major limitation of existing open-domain chatbot research is its singular focu…
Online conversations are particularly susceptible to derailment, which can manifest itself in the form of toxic communication patterns like disrespectful comments or verbal abuse. Forecasting conversa…
To address the challenge of policy learning in open-domain multi-turn conversation, we propose to represent prior information about dialog transitions as a graph and learn a graph grounded dialog poli…
Those models take a contrastive learning approach, where they build binary classifiers to differentiate positive, or coherent examples from negative, or incoherent dialogues. Those classifiers are usu…
Effective interlocutors account for the uncertain goals, beliefs, and emotions of others. But even the best human conversationalist cannot perfectly anticipate the trajectory of a dialogue. How well c…
“All these situations share an underlying structured decision problem in the face of uncertainty, where communicating and collaborating with others is often critical to arrive at the best solution. D…
Abstract While belief tracking is known to be important in allowing statistical dialog systems to manage dialogs in a highly robust manner, until recently little attention has been given to analysing …
Task-oriented conversational systems often use dialogue state tracking to represent the user’s intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, of…
Conversational AI assistants promise to help users achieve a task through natural language. Interpreting simple instructions like please turn on the lights is relatively straightforward, but to handle…
We propose DialogueReason, a reasoning paradigm that uncovers the lost roles in monologue-style reasoning models, aiming to boost diversity and coherency of the reasoning process. Recent advances in R…
Deploying Large Language Models (LLMs) in streaming applications such as multi-round dialogue, where long interactions are expected, is urgently needed but poses two major challenges. Firstly, during …
Recently, the development of large language models (LLMs) has been significantly enhanced the question answering and dialogue generation, and makes them become increasingly popular in current practica…
“This paper proposes a hybrid approach that leverages LLMs, in particular GPT-4, to enhance pipeline-based CAs. Using this approach, maintainers of existing CAs can adopt new domains and overcome the …
 Human conversations are guided by short-term and longterm goals. We study how to plan short-term goal sequ…
In light of this finding, we propose a novel ChatCRS framework to decompose the complex CRS task into several subtasks through the implementation of 1) a knowledge retrieval agent using a tool-augment…
“This paper delves into an advanced implementation of Chain-of-Thought-Prompting in Large Language Models, focusing on the use of tools (or "plug-ins") within the explicit reasoning paths generated by…
Proactive dialogue system is able to lead the conversation to a goal topic and has advantaged potential in bargain, persuasion and negotiation. Current corpus-based learning manner limits its practica…
The alignment of Large Language Models (LLMs) for multi-turn conversations typically relies on reward signals derived from the content of the text. This approach, however, overlooks a rich, complement…
 Existing studies in dialogue system research mostly treat task-oriented dialogue and chitchat as separate domains. Towards …
Unlike empathetic dialogues, the system in emotional support conversations (ESC) is expected to not only convey empathy for comforting the help-seeker, but also proactively assist in exploring and add…
As in any conversation in natural language, queries in conversational search may involve omissions, references to previous turns, and ambiguities [32]. Thus, a primary challenge for effective conversa…
Abstract. The increasing demand for web-based digital assistants has given a rapid rise in the interest of the Information Retrieval (IR) community towards the field of conversational question answeri…
“The modern recommendation systems found in commercial applications are largely based on implicit preferences, such as a user’s history of web page clicks, item purchases, or media streams, with the r…
We present MultiChallenge, a pioneering benchmark evaluating large language models (LLMs) on conducting multi-turn conversations with human users, a crucial yet underexamined capability for their appl…
The present paper surveys neural approaches to conversational AI that have been developed in the last few years. We group conversational systems into three categories: (1) question answering agents, (…
Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction.…
“In this paper, we attempt to systematise the literature about the attested problems of neural conversation models (conditional language models realised with neural networks) used as chat-partner simu…
The current literature on presupposition focuses almost exclusively on the projection problem: the question of how and why the presuppositions of atomic clauses are projected to complex sentences whic…
 We study a conversational reasoning model that strategically traverses through a largescale common…
Argumentation is the process by which humans rationally elaborate their thoughts and opinions in written (e.g., essays) or spoken (e.g., debates) contexts. Argument Mining research, however, has been …
In proactive dialogue, the challenge lies not just in generating responses but in steering conversations toward predetermined goals, a task where Large Language Models (LLMs) typically struggle due to…
Humans communicate with increasing efficiency in multi-turn interactions, by adapting their language and forming ad-hoc conventions. In contrast, prior work shows that LLMs do not naturally show this …
We investigate proactivity, the capacity of a dialogue system to provide relevant information even when not explicitly requested, in the context of task-oriented dialogues. We propose to extend the cu…
In this paper, we demonstrate the limitations of such methods and rethink what it means for AI to be proactive in multi-party, human-AI conversations. We propose that just like humans, rather than mer…
Though great progress has been made for human-machine conversation, current dialogue system is still in its infancy: it usually converses passively and utters words more as a matter of response, rathe…
Conversational systems based on Large Language Models (LLMs), such as ChatGPT, show exceptional proficiency in context understanding and response generation. However, they still possess limitations, s…
Most existing dialogue systems fail to respond properly to potentially unsafe user utterances by either ignoring or passively agreeing with them. To address this issue, we introduce PROSOCIALDIALOG, t…
Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we address this question by d…
Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear probes and other white-…
Much of our daily lives is spent talking to one another, in both ordinary conversation and more specialized settings such as meetings, interviews, classrooms, and courtrooms. It is largely through con…
Linear programming (LP) problems are pervasive in real-life applications. However, despite their apparent simplicity, an untrained user may find it difficult to determine the linear model of their spe…
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 reinf…
We propose a new task of conversational recommendation over multi-type dialogs, where the bots can proactively and naturally lead a conversation from a non-recommendation dialog (e.g., QA) to a recomm…
Task-oriented dialogue systems often face difficulties when user utterances seem semantically complete but lack necessary structural information for appropriate system action. This arises because user…
Task-oriented Dialogue (TOD) Systems aim to build dialogue systems that assist users in accomplishing specific goals, such as booking a hotel or a restaurant. Traditional TODs rely on domain-specific …