相关论文: Recipes for Safety in Open-domain Chatbots

One of the main weaknesses of current chatbots or dialogue systems is that they do not learn online during conversations after they are deployed. This is a major loss of opportunity. Clearly, each human user has a great deal of knowledge…

The study illustrates a first step towards an ongoing work aimed at developing a dataset of dialogues potentially useful for customer service conversation management between humans and AI chatbots. The approach exploits ChatGPT 3.5 to…

Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Knowledge problem. Furthermore, we believe that large language…

Nowadays, open-domain dialogue models can generate acceptable responses according to the historical context based on the large-scale pre-trained language models. However, they generally concatenate the dialogue history directly as the model…

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,…

Diffusion models (DMs) have been investigated in various domains due to their ability to generate high-quality data, thereby attracting significant attention. However, similar to traditional deep learning systems, there also exist potential…

With significant advances in generative AI, new technologies are rapidly being deployed with generative components. Generative models are typically trained on large datasets, resulting in model behaviors that can mimic the worst of the…

This paper delves into the realm of ChatGPT, an AI-powered chatbot that utilizes topic modeling and reinforcement learning to generate natural responses. Although ChatGPT holds immense promise across various industries, such as customer…

Training the generative models with minimal corpus is one of the critical challenges for building open-domain dialogue systems. Existing methods tend to use the meta-learning framework which pre-trains the parameters on all non-target tasks…

LLM-driven dialog systems are used in a diverse set of applications, ranging from healthcare to customer service. However, given their generalization capability, it is difficult to ensure that these chatbots stay within the boundaries of…

Dialogue systems are usually categorized into two types, open-domain and task-oriented. The first one focuses on chatting with users and making them engage in the conversations, where selecting a proper topic to fit the dialogue context is…

All AI models are susceptible to learning biases in data that they are trained on. For generative dialogue models, being trained on real human conversations containing unbalanced gender and race/ethnicity references can lead to models that…

Evaluating and understanding the inappropriateness of chatbot behaviors can be challenging, particularly for chatbot designers without technical backgrounds. To democratize the debugging process of chatbot misbehaviors for non-technical…

Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses when interacting with real users. This phenomenon might mainly result from the…

Predictive human models often need to adapt their parameters online from human data. This raises previously ignored safety-related questions for robots relying on these models such as what the model could learn online and how quickly could…

Large Language Model (LLMs) such as ChatGPT that exhibit generative AI capabilities are facing accelerated adoption and innovation. The increased presence of Generative AI (GAI) inevitably raises concerns about the risks and safety…

On-the-job learning consists in continuously learning while being used in production, in an open environment, meaning that the system has to deal on its own with situations and elements never seen before. The kind of systems that seem to be…

Frozen models trained to mimic static datasets can never improve their performance. Models that can employ internet-retrieval for up-to-date information and obtain feedback from humans during deployment provide the promise of both adapting…

Morality in dialogue systems has raised great attention in research recently. A moral dialogue system aligned with users' values could enhance conversation engagement and user connections. In this paper, we propose a framework, MoralDial to…

Retrieval-based chatbot selects the appropriate response from candidates according to the context, which heavily depends on a response selection module. A response selection module is generally a scoring model to evaluate candidates and is…