Related papers: Bootstrapping incremental dialogue systems: using …

Retrieval-augmented generation (RAG) is key to enhancing large language models (LLMs) to systematically access richer factual knowledge. Yet, using RAG brings intrinsic challenges, as LLMs must deal with potentially conflicting knowledge,…

Reinforcement learning from human or AI feedback (RLHF/RLAIF) for speech-in/speech-out dialogue systems (SDS) remains underexplored, with prior work largely limited to single semantic rewards applied at the utterance level. Such setups…

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…

We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent models its knowledge as…

The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reasoning through Multi-Agent Debate (MAD) has emerged as a…

Real human conversation data are complicated, heterogeneous, and noisy, from which building open-domain dialogue systems remains a challenging task. In fact, such dialogue data still contains a wealth of information and knowledge, however,…

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap…

Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they have many benefits. By using speech as the primary communication medium, a computer interface can facilitate swift, human-like acquisition of…

We consider the task of building a dialogue system that can motivate users to adopt positive lifestyle changes: Motivational Interviewing. Addressing such a task requires a system that can infer \textit{how} to motivate a user effectively.…

Maintaining a consistent persona is a key quality for any open domain dialogue system. Current state-of-the-art systems do this by training agents with supervised learning or online reinforcement learning (RL). However, systems trained with…

Current research in dialogue systems is focused on conversational assistants working on short conversations in either task-oriented or open domain settings. In this paper, we focus on improving task-based conversational assistants online,…

Reinforcement learning (RL) algorithms update an agent's parameters according to one of several possible rules, discovered manually through years of research. Automating the discovery of update rules from data could lead to more efficient…

Zero-shot Dialogue State Tracking (DST) addresses the challenge of acquiring and annotating task-oriented dialogues, which can be time-consuming and costly. However, DST extends beyond simple slot-filling and requires effective updating…

Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead…

In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model. We present a novel reinforcement learning (RL) method for continuous state and action spaces that…

Few-shot dialogue state tracking (DST) with Large Language Models (LLM) relies on an effective and efficient conversation retriever to find similar in-context examples for prompt learning. Previous works use raw dialogue context as search…

Contextually aware intelligent agents are often required to understand the users and their surroundings in real-time. Our goal is to build Artificial Intelligence (AI) systems that can assist children in their learning process. Within such…

Learning by interaction is the key to skill acquisition for most living organisms, which is formally called Reinforcement Learning (RL). RL is efficient in finding optimal policies for endowing complex systems with sophisticated behavior.…

Maintaining engagement and consistency is particularly important in dialogue systems. Existing works have improved the performance of dialogue systems by intentionally learning interlocutor personas with sophisticated network structures.…

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL.To solve this problem, many strategies…