Related papers: Measuring Conversational Fluidity in Automated Dia…

The field of eXplainable Artificial Intelligence (XAI) is increasingly recognizing the need to personalize and/or interactively adapt the explanation to better reflect users' explanation needs. While dialogue-based approaches to XAI have…

Recently, ``textless" speech language models (SLMs) based on speech units have made huge progress in generating naturalistic speech, including non-verbal vocalizations. However, the generated speech samples often lack semantic coherence. In…

In this work, we evaluate various existing dialogue relevance metrics, find strong dependency on the dataset, often with poor correlation with human scores of relevance, and propose modifications to reduce data requirements and domain…

Surveys and interviews are widely used for collecting insights on emerging or hypothetical scenarios. Traditional human-led methods often face challenges related to cost, scalability, and consistency. Recently, various domains have begun to…

Today, as seen in smart speakers, spoken dialogue technology is rapidly advancing to enable human-like interaction. However, current dialogue systems cannot pay attention not only to the content of speech, but also to the way of speaking…

Multi-agent debate (MAD) is an emerging approach to improving the reasoning capabilities of large language models (LLMs). Existing MAD methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is…

We aim to overcome the lack of diversity in responses of current dialogue systems and to develop a dialogue system that is engaging as a conversational partner. We propose a generator-evaluator model that evaluates multiple responses…

Cyber-physical systems like autonomous vehicles are tested in simulation before deployment, using domain-specific programs for scenario specification. To aid the testing of autonomous vehicles in simulation, we design a natural language…

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…

Automated approaches to answer patient-posed health questions are rising, but selecting among systems requires reliable evaluation. The current gold standard for evaluating the free-text artificial intelligence (AI) responses--human expert…

In this paper, we present a statistical approach for dialogue act processing in the dialogue component of the speech-to-speech translation system \vm. Statistics in dialogue processing is used to predict follow-up dialogue acts. As an…

Although current state-of-the-art language models have achieved impressive results in numerous natural language processing tasks, still they could not solve the problem of producing repetitive, dull and sometimes inconsistent text in…

We present an end-to-end voice-based conversational agent that is able to engage in naturalistic multi-turn dialogue and align with the interlocutor's conversational style. The system uses a series of deep neural network components for…

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…

In second language learning, scenario-based conversation practice is important for language learners to achieve fluency in speaking, but students often lack sufficient opportunities to practice their conversational skills with qualified…

Stylistic variation is critical to render the utterances generated by conversational agents natural and engaging. In this paper, we focus on sequence-to-sequence models for open-domain dialogue response generation and propose a new method…

Training dialog policies for speech-based virtual assistants requires a plethora of conversational data. The data collection phase is often expensive and time consuming due to human involvement. To address this issue, a common solution is…

We propose LLM-Eval, a unified multi-dimensional automatic evaluation method for open-domain conversations with large language models (LLMs). Existing evaluation methods often rely on human annotations, ground-truth responses, or multiple…

One challenge for dialogue agents is recognizing feelings in the conversation partner and replying accordingly, a key communicative skill. While it is straightforward for humans to recognize and acknowledge others' feelings in a…

Automated evaluation metrics as a stand-in for manual evaluation are an essential part of the development of text-generation tasks such as text summarization. However, while the field has progressed, our standard metrics have not -- for…